Compare commits

..

2 Commits

Author SHA1 Message Date
Bruce MacDonald
938be81c45 Add TODO 2024-05-10 10:15:22 -07:00
Bruce MacDonald
19ce10e49e add a /tokenize endpoint 2024-05-10 10:13:50 -07:00
25 changed files with 385 additions and 546 deletions

View File

@@ -359,7 +359,7 @@ See the [API documentation](./docs/api.md) for all endpoints.
- [Testcontainers](https://testcontainers.com/modules/ollama/)
- [Portkey](https://portkey.ai/docs/welcome/integration-guides/ollama)
- [PromptingTools.jl](https://github.com/svilupp/PromptingTools.jl) with an [example](https://svilupp.github.io/PromptingTools.jl/dev/examples/working_with_ollama)
- [LlamaScript](https://github.com/Project-Llama/llamascript)
- [LlamaScript](https://github.com/WolfTheDeveloper/llamascript)
### Mobile
- [Enchanted](https://github.com/AugustDev/enchanted)

View File

@@ -354,15 +354,6 @@ func (c *Client) List(ctx context.Context) (*ListResponse, error) {
return &lr, nil
}
// List running models.
func (c *Client) ListRunning(ctx context.Context) (*ListResponse, error) {
var lr ListResponse
if err := c.do(ctx, http.MethodGet, "/api/ps", nil, &lr); err != nil {
return nil, err
}
return &lr, nil
}
// Copy copies a model - creating a model with another name from an existing
// model.
func (c *Client) Copy(ctx context.Context, req *CopyRequest) error {

View File

@@ -195,19 +195,28 @@ type EmbeddingResponse struct {
Embedding []float64 `json:"embedding"`
}
type TokenizeRequest struct {
Model string `json:"model"`
Prompt string `json:"prompt"`
KeepAlive *Duration `json:"keep_alive,omitempty"`
Options map[string]interface{} `json:"options"`
}
type TokenizeResponse struct {
Tokens []int `json:"tokens"`
}
// CreateRequest is the request passed to [Client.Create].
type CreateRequest struct {
Model string `json:"model"`
Path string `json:"path"`
Modelfile string `json:"modelfile"`
Stream *bool `json:"stream,omitempty"`
Quantize string `json:"quantize,omitempty"`
Model string `json:"model"`
Path string `json:"path"`
Modelfile string `json:"modelfile"`
Stream *bool `json:"stream,omitempty"`
Quantization string `json:"quantization,omitempty"`
// Name is deprecated, see Model
Name string `json:"name"`
// Quantization is deprecated, see Quantize
Quantization string `json:"quantization,omitempty"`
}
// DeleteRequest is the request passed to [Client.Delete].
@@ -289,12 +298,10 @@ type ListResponse struct {
type ModelResponse struct {
Name string `json:"name"`
Model string `json:"model"`
ModifiedAt time.Time `json:"modified_at,omitempty"`
ModifiedAt time.Time `json:"modified_at"`
Size int64 `json:"size"`
Digest string `json:"digest"`
Details ModelDetails `json:"details,omitempty"`
ExpiresAt time.Time `json:"expires_at,omitempty"`
SizeVRAM int64 `json:"size_vram,omitempty"`
}
type TokenResponse struct {

View File

@@ -12,7 +12,6 @@ import (
"fmt"
"io"
"log"
"math"
"net"
"net/http"
"os"
@@ -143,9 +142,9 @@ func CreateHandler(cmd *cobra.Command, args []string) error {
return nil
}
quantize, _ := cmd.Flags().GetString("quantize")
quantization, _ := cmd.Flags().GetString("quantization")
request := api.CreateRequest{Name: args[0], Modelfile: modelfile.String(), Quantize: quantize}
request := api.CreateRequest{Name: args[0], Modelfile: modelfile.String(), Quantization: quantization}
if err := client.Create(cmd.Context(), &request, fn); err != nil {
return err
}
@@ -325,18 +324,6 @@ func RunHandler(cmd *cobra.Command, args []string) error {
}
opts.Format = format
keepAlive, err := cmd.Flags().GetString("keepalive")
if err != nil {
return err
}
if keepAlive != "" {
d, err := time.ParseDuration(keepAlive)
if err != nil {
return err
}
opts.KeepAlive = &api.Duration{Duration: d}
}
prompts := args[1:]
// prepend stdin to the prompt if provided
if !term.IsTerminal(int(os.Stdin.Fd())) {
@@ -509,52 +496,6 @@ func ListHandler(cmd *cobra.Command, args []string) error {
return nil
}
func ListRunningHandler(cmd *cobra.Command, args []string) error {
client, err := api.ClientFromEnvironment()
if err != nil {
return err
}
models, err := client.ListRunning(cmd.Context())
if err != nil {
return err
}
var data [][]string
for _, m := range models.Models {
if len(args) == 0 || strings.HasPrefix(m.Name, args[0]) {
var procStr string
switch {
case m.SizeVRAM == 0:
procStr = "100% CPU"
case m.SizeVRAM == m.Size:
procStr = "100% GPU"
case m.SizeVRAM > m.Size || m.Size == 0:
procStr = "Unknown"
default:
sizeCPU := m.Size - m.SizeVRAM
cpuPercent := math.Round(float64(sizeCPU) / float64(m.Size) * 100)
procStr = fmt.Sprintf("%d%%/%d%% CPU/GPU", int(cpuPercent), int(100-cpuPercent))
}
data = append(data, []string{m.Name, m.Digest[:12], format.HumanBytes(m.Size), procStr, format.HumanTime(m.ExpiresAt, "Never")})
}
}
table := tablewriter.NewWriter(os.Stdout)
table.SetHeader([]string{"NAME", "ID", "SIZE", "PROCESSOR", "UNTIL"})
table.SetHeaderAlignment(tablewriter.ALIGN_LEFT)
table.SetAlignment(tablewriter.ALIGN_LEFT)
table.SetHeaderLine(false)
table.SetBorder(false)
table.SetNoWhiteSpace(true)
table.SetTablePadding("\t")
table.AppendBulk(data)
table.Render()
return nil
}
func DeleteHandler(cmd *cobra.Command, args []string) error {
client, err := api.ClientFromEnvironment()
if err != nil {
@@ -731,7 +672,6 @@ type runOptions struct {
Images []api.ImageData
Options map[string]interface{}
MultiModal bool
KeepAlive *api.Duration
}
type displayResponseState struct {
@@ -826,10 +766,6 @@ func chat(cmd *cobra.Command, opts runOptions) (*api.Message, error) {
Options: opts.Options,
}
if opts.KeepAlive != nil {
req.KeepAlive = opts.KeepAlive
}
if err := client.Chat(cancelCtx, req, fn); err != nil {
if errors.Is(err, context.Canceled) {
return nil, nil
@@ -905,15 +841,14 @@ func generate(cmd *cobra.Command, opts runOptions) error {
}
request := api.GenerateRequest{
Model: opts.Model,
Prompt: opts.Prompt,
Context: generateContext,
Images: opts.Images,
Format: opts.Format,
System: opts.System,
Template: opts.Template,
Options: opts.Options,
KeepAlive: opts.KeepAlive,
Model: opts.Model,
Prompt: opts.Prompt,
Context: generateContext,
Images: opts.Images,
Format: opts.Format,
System: opts.System,
Template: opts.Template,
Options: opts.Options,
}
if err := client.Generate(ctx, &request, fn); err != nil {
@@ -1115,8 +1050,8 @@ func NewCLI() *cobra.Command {
RunE: CreateHandler,
}
createCmd.Flags().StringP("file", "f", "Modelfile", "Name of the Modelfile")
createCmd.Flags().StringP("quantize", "q", "", "Quantize model to this level (e.g. q4_0)")
createCmd.Flags().StringP("file", "f", "Modelfile", "Name of the Modelfile (default \"Modelfile\")")
createCmd.Flags().StringP("quantization", "q", "", "Quantization level.")
showCmd := &cobra.Command{
Use: "show MODEL",
@@ -1140,7 +1075,6 @@ func NewCLI() *cobra.Command {
RunE: RunHandler,
}
runCmd.Flags().String("keepalive", "", "Duration to keep a model loaded (e.g. 5m)")
runCmd.Flags().Bool("verbose", false, "Show timings for response")
runCmd.Flags().Bool("insecure", false, "Use an insecure registry")
runCmd.Flags().Bool("nowordwrap", false, "Don't wrap words to the next line automatically")
@@ -1156,9 +1090,9 @@ func NewCLI() *cobra.Command {
Environment Variables:
OLLAMA_HOST The host:port to bind to (default "127.0.0.1:11434")
OLLAMA_ORIGINS A comma separated list of allowed origins
OLLAMA_MODELS The path to the models directory (default "~/.ollama/models")
OLLAMA_KEEP_ALIVE The duration that models stay loaded in memory (default "5m")
OLLAMA_ORIGINS A comma separated list of allowed origins.
OLLAMA_MODELS The path to the models directory (default is "~/.ollama/models")
OLLAMA_KEEP_ALIVE The duration that models stay loaded in memory (default is "5m")
OLLAMA_DEBUG Set to 1 to enable additional debug logging
`)
@@ -1189,14 +1123,6 @@ Environment Variables:
PreRunE: checkServerHeartbeat,
RunE: ListHandler,
}
psCmd := &cobra.Command{
Use: "ps",
Short: "List running models",
PreRunE: checkServerHeartbeat,
RunE: ListRunningHandler,
}
copyCmd := &cobra.Command{
Use: "cp SOURCE DESTINATION",
Short: "Copy a model",
@@ -1220,7 +1146,6 @@ Environment Variables:
pullCmd,
pushCmd,
listCmd,
psCmd,
copyCmd,
deleteCmd,
} {
@@ -1235,7 +1160,6 @@ Environment Variables:
pullCmd,
pushCmd,
listCmd,
psCmd,
copyCmd,
deleteCmd,
)

View File

@@ -17,7 +17,6 @@ import (
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/progress"
"github.com/ollama/ollama/readline"
"github.com/ollama/ollama/types/errtypes"
)
type MultilineState int
@@ -57,11 +56,6 @@ func loadModel(cmd *cobra.Command, opts *runOptions) error {
Model: opts.Model,
Messages: []api.Message{},
}
if opts.KeepAlive != nil {
chatReq.KeepAlive = opts.KeepAlive
}
err = client.Chat(cmd.Context(), chatReq, func(resp api.ChatResponse) error {
p.StopAndClear()
if len(opts.Messages) > 0 {
@@ -282,20 +276,13 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error {
fn := func(resp api.ProgressResponse) error { return nil }
err = client.Create(cmd.Context(), req, fn)
if err != nil {
if strings.Contains(err.Error(), errtypes.InvalidModelNameErrMsg) {
fmt.Printf("error: The model name '%s' is invalid\n", args[1])
continue
}
fmt.Println("error: couldn't save model")
return err
}
fmt.Printf("Created new model '%s'\n", args[1])
continue
case strings.HasPrefix(line, "/clear"):
opts.Messages = []api.Message{}
if opts.System != "" {
newMessage := api.Message{Role: "system", Content: opts.System}
opts.Messages = append(opts.Messages, newMessage)
}
fmt.Println("Cleared session context")
continue
case strings.HasPrefix(line, "/set"):

View File

@@ -797,9 +797,9 @@ curl http://localhost:11434/api/show -d '{
```json
{
"modelfile": "# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llava:latest\n\nFROM /Users/matt/.ollama/models/blobs/sha256:200765e1283640ffbd013184bf496e261032fa75b99498a9613be4e94d63ad52\nTEMPLATE \"\"\"{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: \"\"\"\nPARAMETER num_ctx 4096\nPARAMETER stop \"\u003c/s\u003e\"\nPARAMETER stop \"USER:\"\nPARAMETER stop \"ASSISTANT:\"",
"parameters": "num_ctx 4096\nstop \u003c/s\u003e\nstop USER:\nstop ASSISTANT:",
"template": "{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: ",
"modelfile": "# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llava:latest\n\nFROM /Users/matt/.ollama/models/blobs/sha256:200765e1283640ffbd013184bf496e261032fa75b99498a9613be4e94d63ad52\nTEMPLATE \"\"\"{{ .System }}\nUSER: {{ .Prompt }}\nASSSISTANT: \"\"\"\nPARAMETER num_ctx 4096\nPARAMETER stop \"\u003c/s\u003e\"\nPARAMETER stop \"USER:\"\nPARAMETER stop \"ASSSISTANT:\"",
"parameters": "num_ctx 4096\nstop \u003c/s\u003e\nstop USER:\nstop ASSSISTANT:",
"template": "{{ .System }}\nUSER: {{ .Prompt }}\nASSSISTANT: ",
"details": {
"format": "gguf",
"family": "llama",

View File

@@ -80,19 +80,17 @@ If Ollama is run as a systemd service, environment variables should be set using
### Setting environment variables on Windows
On Windows, Ollama inherits your user and system environment variables.
On windows, Ollama inherits your user and system environment variables.
1. First Quit Ollama by clicking on it in the task bar.
1. First Quit Ollama by clicking on it in the task bar
2. Start the Settings (Windows 11) or Control Panel (Windows 10) application and search for _environment variables_.
2. Edit system environment variables from the control panel
3. Click on _Edit environment variables for your account_.
3. Edit or create New variable(s) for your user account for `OLLAMA_HOST`, `OLLAMA_MODELS`, etc.
4. Edit or create a new variable for your user account for `OLLAMA_HOST`, `OLLAMA_MODELS`, etc.
4. Click OK/Apply to save
5. Click OK/Apply to save.
6. Start the Ollama application from the Windows Start menu.
5. Run `ollama` from a new terminal window
## How can I expose Ollama on my network?
@@ -239,4 +237,4 @@ If you wish to override the `OLLAMA_KEEP_ALIVE` setting, use the `keep_alive` AP
If too many requests are sent to the server, it will respond with a 503 error
indicating the server is overloaded. You can adjust how many requests may be
queue by setting `OLLAMA_MAX_QUEUE`
queue by setting `OLLAMA_MAX_QUEUE`

View File

@@ -60,9 +60,7 @@ func humanTime(t time.Time, zeroValue string) string {
}
delta := time.Since(t)
if int(delta.Hours())/24/365 < -20 {
return "Forever"
} else if delta < 0 {
if delta < 0 {
return humanDuration(-delta) + " from now"
}

View File

@@ -32,14 +32,4 @@ func TestHumanTime(t *testing.T) {
v := now.Add(800 * time.Millisecond)
assertEqual(t, HumanTime(v, ""), "Less than a second from now")
})
t.Run("time way in the future", func(t *testing.T) {
v := now.Add(24 * time.Hour * 365 * 200)
assertEqual(t, HumanTime(v, ""), "Forever")
})
t.Run("time way in the future lowercase", func(t *testing.T) {
v := now.Add(24 * time.Hour * 365 * 200)
assertEqual(t, HumanTimeLower(v, ""), "forever")
})
}

62
go.mod
View File

@@ -1,38 +1,36 @@
module github.com/ollama/ollama
go 1.22.0
go 1.22
toolchain go1.22.0
require (
github.com/containerd/console v1.0.3
github.com/d4l3k/go-bfloat16 v0.0.0-20211005043715-690c3bdd05f1
github.com/emirpasic/gods v1.18.1
github.com/gin-gonic/gin v1.10.0
github.com/golang/protobuf v1.5.4 // indirect
github.com/google/uuid v1.1.2
github.com/gin-gonic/gin v1.9.1
github.com/golang/protobuf v1.5.0 // indirect
github.com/google/uuid v1.0.0
github.com/mitchellh/mapstructure v1.5.0
github.com/olekukonko/tablewriter v0.0.5
github.com/spf13/cobra v1.7.0
github.com/stretchr/testify v1.9.0
github.com/stretchr/testify v1.8.4
github.com/x448/float16 v0.8.4
golang.org/x/sync v0.3.0
)
require (
github.com/nlpodyssey/gopickle v0.3.0
github.com/pdevine/tensor v0.0.0-20240510204454-f88f4562727c
github.com/pdevine/tensor v0.0.0-20240228013915-64ccaa8d9ca9
)
require (
github.com/apache/arrow/go/arrow v0.0.0-20211112161151-bc219186db40 // indirect
github.com/bytedance/sonic/loader v0.1.1 // indirect
github.com/apache/arrow/go/arrow v0.0.0-20201229220542-30ce2eb5d4dc // indirect
github.com/chewxy/hm v1.0.0 // indirect
github.com/chewxy/math32 v1.10.1 // indirect
github.com/cloudwego/base64x v0.1.4 // indirect
github.com/cloudwego/iasm v0.2.0 // indirect
github.com/chewxy/math32 v1.0.8 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/gogo/protobuf v1.3.2 // indirect
github.com/google/flatbuffers v24.3.25+incompatible // indirect
github.com/kr/text v0.2.0 // indirect
github.com/google/flatbuffers v1.12.0 // indirect
github.com/mattn/go-runewidth v0.0.14 // indirect
github.com/pkg/errors v0.9.1 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
@@ -40,38 +38,40 @@ require (
github.com/xtgo/set v1.0.0 // indirect
go4.org/unsafe/assume-no-moving-gc v0.0.0-20231121144256-b99613f794b6 // indirect
golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 // indirect
gonum.org/v1/gonum v0.15.0 // indirect
gonum.org/v1/gonum v0.8.2 // indirect
gorgonia.org/vecf32 v0.9.0 // indirect
gorgonia.org/vecf64 v0.9.0 // indirect
)
require (
github.com/bytedance/sonic v1.11.6 // indirect
github.com/gabriel-vasile/mimetype v1.4.3 // indirect
github.com/gin-contrib/cors v1.7.2
github.com/bytedance/sonic v1.9.1 // indirect
github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
github.com/gabriel-vasile/mimetype v1.4.2 // indirect
github.com/gin-contrib/cors v1.4.0
github.com/gin-contrib/sse v0.1.0 // indirect
github.com/go-playground/locales v0.14.1 // indirect
github.com/go-playground/universal-translator v0.18.1 // indirect
github.com/go-playground/validator/v10 v10.20.0 // indirect
github.com/go-playground/validator/v10 v10.14.0 // indirect
github.com/goccy/go-json v0.10.2 // indirect
github.com/google/go-cmp v0.5.9 // indirect
github.com/inconshreveable/mousetrap v1.1.0 // indirect
github.com/json-iterator/go v1.1.12 // indirect
github.com/klauspost/cpuid/v2 v2.2.7 // indirect
github.com/leodido/go-urn v1.4.0 // indirect
github.com/mattn/go-isatty v0.0.20 // indirect
github.com/klauspost/cpuid/v2 v2.2.4 // indirect
github.com/leodido/go-urn v1.2.4 // indirect
github.com/mattn/go-isatty v0.0.19 // indirect
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
github.com/modern-go/reflect2 v1.0.2 // indirect
github.com/pelletier/go-toml/v2 v2.2.2 // indirect
github.com/pelletier/go-toml/v2 v2.0.8 // indirect
github.com/spf13/pflag v1.0.5 // indirect
github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
github.com/ugorji/go/codec v1.2.12 // indirect
golang.org/x/arch v0.8.0 // indirect
golang.org/x/crypto v0.23.0
golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa
golang.org/x/net v0.25.0 // indirect
golang.org/x/sys v0.20.0
golang.org/x/term v0.20.0
golang.org/x/text v0.15.0 // indirect
google.golang.org/protobuf v1.34.1
github.com/ugorji/go/codec v1.2.11 // indirect
golang.org/x/arch v0.3.0 // indirect
golang.org/x/crypto v0.14.0
golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63
golang.org/x/net v0.17.0 // indirect
golang.org/x/sys v0.13.0
golang.org/x/term v0.13.0
golang.org/x/text v0.14.0 // indirect
google.golang.org/protobuf v1.30.0
gopkg.in/yaml.v3 v3.0.1 // indirect
)

244
go.sum
View File

@@ -1,32 +1,22 @@
cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
cloud.google.com/go v0.34.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
gioui.org v0.0.0-20210308172011-57750fc8a0a6/go.mod h1:RSH6KIUZ0p2xy5zHDxgAM4zumjgTw83q2ge/PI+yyw8=
github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
github.com/ajstarks/svgo v0.0.0-20180226025133-644b8db467af/go.mod h1:K08gAheRH3/J6wwsYMMT4xOr94bZjxIelGM0+d/wbFw=
github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
github.com/apache/arrow/go/arrow v0.0.0-20211112161151-bc219186db40 h1:q4dksr6ICHXqG5hm0ZW5IHyeEJXoIJSOZeBLmWPNeIQ=
github.com/apache/arrow/go/arrow v0.0.0-20211112161151-bc219186db40/go.mod h1:Q7yQnSMnLvcXlZ8RV+jwz/6y1rQTqbX6C82SndT52Zs=
github.com/boombuler/barcode v1.0.0/go.mod h1:paBWMcWSl3LHKBqUq+rly7CNSldXjb2rDl3JlRe0mD8=
github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0=
github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU=
github.com/apache/arrow/go/arrow v0.0.0-20201229220542-30ce2eb5d4dc h1:zvQ6w7KwtQWgMQiewOF9tFtundRMVZFSAksNV6ogzuY=
github.com/apache/arrow/go/arrow v0.0.0-20201229220542-30ce2eb5d4dc/go.mod h1:c9sxoIT3YgLxH4UhLOCKaBlEojuMhVYpk4Ntv3opUTQ=
github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
github.com/chewxy/hm v1.0.0 h1:zy/TSv3LV2nD3dwUEQL2VhXeoXbb9QkpmdRAVUFiA6k=
github.com/chewxy/hm v1.0.0/go.mod h1:qg9YI4q6Fkj/whwHR1D+bOGeF7SniIP40VweVepLjg0=
github.com/chewxy/math32 v1.0.0/go.mod h1:Miac6hA1ohdDUTagnvJy/q+aNnEk16qWUdb8ZVhvCN0=
github.com/chewxy/math32 v1.10.1 h1:LFpeY0SLJXeaiej/eIp2L40VYfscTvKh/FSEZ68uMkU=
github.com/chewxy/math32 v1.10.1/go.mod h1:dOB2rcuFrCn6UHrze36WSLVPKtzPMRAQvBvUwkSsLqs=
github.com/chewxy/math32 v1.0.8 h1:fU5E4Ec4Z+5RtRAi3TovSxUjQPkgRh+HbP7tKB2OFbM=
github.com/chewxy/math32 v1.0.8/go.mod h1:dOB2rcuFrCn6UHrze36WSLVPKtzPMRAQvBvUwkSsLqs=
github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y=
github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
github.com/cncf/udpa/go v0.0.0-20201120205902-5459f2c99403/go.mod h1:WmhPx2Nbnhtbo57+VJT5O0JRkEi1Wbu0z5j0R8u5Hbk=
github.com/cncf/xds/go v0.0.0-20210312221358-fbca930ec8ed/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
github.com/containerd/console v1.0.3 h1:lIr7SlA5PxZyMV30bDW0MGbiOPXwc63yRuCP0ARubLw=
github.com/containerd/console v1.0.3/go.mod h1:7LqA/THxQ86k76b8c/EMSiaJ3h1eZkMkXar0TQ1gf3U=
github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
@@ -41,35 +31,30 @@ github.com/emirpasic/gods v1.18.1/go.mod h1:8tpGGwCnJ5H4r6BWwaV6OrWmMoPhUl5jm/FM
github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
github.com/envoyproxy/go-control-plane v0.9.9-0.20201210154907-fd9021fe5dad/go.mod h1:cXg6YxExXjJnVBQHBLXeUAgxn2UodCpnH306RInaBQk=
github.com/envoyproxy/go-control-plane v0.9.9-0.20210217033140-668b12f5399d/go.mod h1:cXg6YxExXjJnVBQHBLXeUAgxn2UodCpnH306RInaBQk=
github.com/envoyproxy/go-control-plane v0.9.9-0.20210512163311-63b5d3c536b0/go.mod h1:hliV/p42l8fGbc6Y9bQ70uLwIvmJyVE5k4iMKlh8wCQ=
github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
github.com/fogleman/gg v1.2.1-0.20190220221249-0403632d5b90/go.mod h1:R/bRT+9gY/C5z7JzPU0zXsXHKM4/ayA+zqcVNZzPa1k=
github.com/fogleman/gg v1.3.0/go.mod h1:R/bRT+9gY/C5z7JzPU0zXsXHKM4/ayA+zqcVNZzPa1k=
github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
github.com/gin-contrib/cors v1.7.2 h1:oLDHxdg8W/XDoN/8zamqk/Drgt4oVZDvaV0YmvVICQw=
github.com/gin-contrib/cors v1.7.2/go.mod h1:SUJVARKgQ40dmrzgXEVxj2m7Ig1v1qIboQkPDTQ9t2E=
github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
github.com/gin-contrib/cors v1.4.0 h1:oJ6gwtUl3lqV0WEIwM/LxPF1QZ5qe2lGWdY2+bz7y0g=
github.com/gin-contrib/cors v1.4.0/go.mod h1:bs9pNM0x/UsmHPBWT2xZz9ROh8xYjYkiURUfmBoMlcs=
github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
github.com/gin-gonic/gin v1.10.0 h1:nTuyha1TYqgedzytsKYqna+DfLos46nTv2ygFy86HFU=
github.com/gin-gonic/gin v1.10.0/go.mod h1:4PMNQiOhvDRa013RKVbsiNwoyezlm2rm0uX/T7kzp5Y=
github.com/go-fonts/dejavu v0.1.0/go.mod h1:4Wt4I4OU2Nq9asgDCteaAaWZOV24E+0/Pwo0gppep4g=
github.com/go-fonts/latin-modern v0.2.0/go.mod h1:rQVLdDMK+mK1xscDwsqM5J8U2jrRa3T0ecnM9pNujks=
github.com/go-fonts/liberation v0.1.1/go.mod h1:K6qoJYypsmfVjWg8KOVDQhLc8UDgIK2HYqyqAO9z7GY=
github.com/go-fonts/stix v0.1.0/go.mod h1:w/c1f0ldAUlJmLBvlbkvVXLAD+tAMqobIIQpmnUIzUY=
github.com/go-gl/glfw v0.0.0-20190409004039-e6da0acd62b1/go.mod h1:vR7hzQXu2zJy9AVAgeJqvqgH9Q5CA+iKCZ2gyEVpxRU=
github.com/go-latex/latex v0.0.0-20210118124228-b3d85cf34e07/go.mod h1:CO1AlKB2CSIqUrmQPqA0gdRIlnLEY0gK5JGjh37zN5U=
github.com/gin-gonic/gin v1.8.1/go.mod h1:ji8BvRH1azfM+SYow9zQ6SZMvR8qOMZHmsCuWR9tTTk=
github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
github.com/go-playground/locales v0.14.0/go.mod h1:sawfccIbzZTqEDETgFXqTho0QybSa7l++s0DH+LDiLs=
github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
github.com/go-playground/universal-translator v0.18.0/go.mod h1:UvRDBj+xPUEGrFYl+lu/H90nyDXpg0fqeB/AQUGNTVA=
github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
github.com/go-playground/validator/v10 v10.20.0 h1:K9ISHbSaI0lyB2eWMPJo+kOS/FBExVwjEviJTixqxL8=
github.com/go-playground/validator/v10 v10.20.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
github.com/go-playground/validator/v10 v10.10.0/go.mod h1:74x4gJWsvQexRdW8Pn3dXSGrTK4nAUsbPlLADvpJkos=
github.com/go-playground/validator/v10 v10.14.0 h1:vgvQWe3XCz3gIeFDm/HnTIbj6UGmg/+t63MyGU2n5js=
github.com/go-playground/validator/v10 v10.14.0/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
github.com/goccy/go-json v0.9.7/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
@@ -87,51 +72,46 @@ github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:W
github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8=
github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
github.com/golang/protobuf v1.5.0 h1:LUVKkCeviFUMKqHa4tXIIij/lbhnMbP7Fn5wKdKkRh4=
github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
github.com/golang/snappy v0.0.3 h1:fHPg5GQYlCeLIPB9BZqMVR5nR9A+IM5zcgeTdjMYmLA=
github.com/golang/snappy v0.0.3/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
github.com/google/flatbuffers v2.0.0+incompatible/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8=
github.com/google/flatbuffers v24.3.25+incompatible h1:CX395cjN9Kke9mmalRoL3d81AtFUxJM+yDthflgJGkI=
github.com/google/flatbuffers v24.3.25+incompatible/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8=
github.com/google/flatbuffers v1.11.0/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8=
github.com/google/flatbuffers v1.12.0 h1:/PtAHvnBY4Kqnx/xCQ3OIV9uYcSFGScBsWI3Oogeh6w=
github.com/google/flatbuffers v1.12.0/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8=
github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
github.com/google/uuid v1.1.2 h1:EVhdT+1Kseyi1/pUmXKaFxYsDNy9RQYkMWRH68J/W7Y=
github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
github.com/google/uuid v1.0.0 h1:b4Gk+7WdP/d3HZH8EJsZpvV7EtDOgaZLtnaNGIu1adA=
github.com/google/uuid v1.0.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
github.com/jung-kurt/gofpdf v1.0.0/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
github.com/jung-kurt/gofpdf v1.0.3-0.20190309125859-24315acbbda5/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
github.com/klauspost/compress v1.13.1 h1:wXr2uRxZTJXHLly6qhJabee5JqIhTRoLBhDOA74hDEQ=
github.com/klauspost/compress v1.13.1/go.mod h1:8dP1Hq4DHOhN9w426knH3Rhby4rFm6D8eO+e+Dq5Gzg=
github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
github.com/klauspost/cpuid/v2 v2.2.7 h1:ZWSB3igEs+d0qvnxR/ZBzXVmxkgt8DdzP6m9pfuVLDM=
github.com/klauspost/cpuid/v2 v2.2.7/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws=
github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M=
github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ=
github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI=
github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
github.com/mattn/go-runewidth v0.0.14 h1:+xnbZSEeDbOIg5/mE6JF0w6n9duR1l3/WmbinWVwUuU=
github.com/mattn/go-runewidth v0.0.14/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
@@ -146,15 +126,12 @@ github.com/nlpodyssey/gopickle v0.3.0 h1:BLUE5gxFLyyNOPzlXxt6GoHEMMxD0qhsE4p0CIQ
github.com/nlpodyssey/gopickle v0.3.0/go.mod h1:f070HJ/yR+eLi5WmM1OXJEGaTpuJEUiib19olXgYha0=
github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
github.com/pdevine/tensor v0.0.0-20240510204454-f88f4562727c h1:GwiUUjKefgvSNmv3NCvI/BL0kDebW6Xa+kcdpdc1mTY=
github.com/pdevine/tensor v0.0.0-20240510204454-f88f4562727c/go.mod h1:PSojXDXF7TbgQiD6kkd98IHOS0QqTyUEaWRiS8+BLu8=
github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6Wq+LM=
github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs=
github.com/phpdave11/gofpdf v1.4.2/go.mod h1:zpO6xFn9yxo3YLyMvW8HcKWVdbNqgIfOOp2dXMnm1mY=
github.com/phpdave11/gofpdi v1.0.12/go.mod h1:vBmVV0Do6hSBHC8uKUQ71JGW+ZGQq74llk/7bXwjDoI=
github.com/pierrec/lz4/v4 v4.1.8 h1:ieHkV+i2BRzngO4Wd/3HGowuZStgq6QkPsD1eolNAO4=
github.com/pierrec/lz4/v4 v4.1.8/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pdevine/tensor v0.0.0-20240228013915-64ccaa8d9ca9 h1:DV4iXjNn6fGeDl1AkZ1I0QB/0DBjrc7kPpxHrmuDzW4=
github.com/pdevine/tensor v0.0.0-20240228013915-64ccaa8d9ca9/go.mod h1:nR7l3gM6ubiOm+mCkmmUyIBUcBAyiUmW6dQrDZhugFE=
github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
@@ -162,11 +139,10 @@ github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZN
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
github.com/rivo/uniseg v0.2.0 h1:S1pD9weZBuJdFmowNwbpi7BJ8TNftyUImj/0WQi72jY=
github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
github.com/rogpeppe/go-internal v1.8.0/go.mod h1:WmiCO8CzOY8rg0OYDC4/i/2WRWAB6poM+XZ2dLUbcbE=
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/ruudk/golang-pdf417 v0.0.0-20181029194003-1af4ab5afa58/go.mod h1:6lfFZQK844Gfx8o5WFuvpxWRwnSoipWe/p622j1v06w=
github.com/spf13/cobra v1.7.0 h1:hyqWnYt1ZQShIddO5kBpj3vu05/++x6tJ6dg8EC572I=
github.com/spf13/cobra v1.7.0/go.mod h1:uLxZILRyS/50WlhOIKD7W6V5bgeIt+4sICxh6uRMrb0=
github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
@@ -174,119 +150,96 @@ github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
github.com/stretchr/testify v1.1.4/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.2.0/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE=
github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
github.com/ugorji/go v1.2.7/go.mod h1:nF9osbDWLy6bDVv/Rtoh6QgnvNDpmCalQV5urGCCS6M=
github.com/ugorji/go/codec v1.2.7/go.mod h1:WGN1fab3R1fzQlVQTkfxVtIBhWDRqOviHU95kRgeqEY=
github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=
github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcYsOfg=
github.com/xtgo/set v1.0.0 h1:6BCNBRv3ORNDQ7fyoJXRv+tstJz3m1JVFQErfeZz2pY=
github.com/xtgo/set v1.0.0/go.mod h1:d3NHzGzSa0NmB2NhFyECA+QdRp29oEn2xbT+TpeFoM8=
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
github.com/yuin/goldmark v1.3.5/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
go.opentelemetry.io/proto/otlp v0.7.0/go.mod h1:PqfVotwruBrMGOCsRd/89rSnXhoiJIqeYNgFYFoEGnI=
go4.org/unsafe/assume-no-moving-gc v0.0.0-20231121144256-b99613f794b6 h1:lGdhQUN/cnWdSH3291CUuxSEqc+AsGTiDxPP3r2J0l4=
go4.org/unsafe/assume-no-moving-gc v0.0.0-20231121144256-b99613f794b6/go.mod h1:FftLjUGFEDu5k8lt0ddY+HcrH/qU/0qk+H8j9/nTl3E=
golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc=
golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/crypto v0.23.0 h1:dIJU/v2J8Mdglj/8rJ6UUOM3Zc9zLZxVZwwxMooUSAI=
golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.14.0 h1:wBqGXzWJW6m1XrIKlAH0Hs1JJ7+9KBwnIO8v66Q9cHc=
golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20180807140117-3d87b88a115f/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20190125153040-c74c464bbbf2/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20191002040644-a1355ae1e2c3/go.mod h1:NOZ3BPKG0ec/BKJQgnvsSFpcKLM5xXVWnvZS97DWHgE=
golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa h1:FRnLl4eNAQl8hwxVVC17teOw8kdjVDVAiFMtgUdTSRQ=
golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa/go.mod h1:zk2irFbV9DP96SEBUUAy67IdHUaZuSnrz1n472HUCLE=
golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63 h1:m64FZMko/V45gv0bNmrNYoDEq8U5YUhetc9cBWKS1TQ=
golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63/go.mod h1:0v4NqG35kSWCMzLaMeX+IQrlSnVE/bqGSyC2cz/9Le8=
golang.org/x/image v0.0.0-20180708004352-c73c2afc3b81/go.mod h1:ux5Hcp/YLpHSI86hEcLt0YII63i6oz57MZXIpbrjZUs=
golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/image v0.0.0-20190910094157-69e4b8554b2a/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/image v0.0.0-20200119044424-58c23975cae1/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/image v0.0.0-20200430140353-33d19683fad8/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/image v0.0.0-20200618115811-c13761719519/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/image v0.0.0-20201208152932-35266b937fa6/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/image v0.0.0-20210216034530-4410531fe030/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
golang.org/x/lint v0.0.0-20210508222113-6edffad5e616/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCcRqshq8CkpyQDoeVncDDYHnLhea+o=
golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20190108225652-1e06a53dbb7e/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
golang.org/x/net v0.0.0-20200904194848-62affa334b73/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
golang.org/x/net v0.0.0-20210614182718-04defd469f4e/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.3.0 h1:ftCYgMx6zT/asHUrPw8BLLscYtGznsLAnjq5RH9P66E=
golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200909081042-eff7692f9009/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210304124612-50617c2ba197/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210330210617-4fbd30eecc44/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210510120138-977fb7262007/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.13.0 h1:Af8nKPmuFypiUBjVoU9V20FiaFXOcuZI21p0ycVYYGE=
golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.20.0 h1:VnkxpohqXaOBYJtBmEppKUG6mXpi+4O6purfc2+sMhw=
golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
golang.org/x/term v0.13.0 h1:bb+I9cTfFazGW51MZqBVmZy7+JEJMouUHTUSKVQLBek=
golang.org/x/term v0.13.0/go.mod h1:LTmsnFJwVN6bCy1rVCoS+qHT1HhALEFxKncY3WNNh4U=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.15.0 h1:h1V/4gjBv8v9cjcR6+AR5+/cIYK5N/WAgiv4xlsEtAk=
golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/tools v0.0.0-20180525024113-a5b4c53f6e8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -294,40 +247,34 @@ golang.org/x/tools v0.0.0-20190206041539-40960b6deb8e/go.mod h1:n7NCudcB/nEzxVGm
golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
golang.org/x/tools v0.0.0-20190927191325-030b2cf1153e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
golang.org/x/tools v0.1.4/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 h1:go1bK/D/BFZV2I8cIQd1NKEZ+0owSTG1fDTci4IqFcE=
golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gonum.org/v1/gonum v0.0.0-20180816165407-929014505bf4/go.mod h1:Y+Yx5eoAFn32cQvJDxZx5Dpnq+c3wtXuadVZAcxbbBo=
gonum.org/v1/gonum v0.8.2 h1:CCXrcPKiGGotvnN6jfUsKk4rRqm7q09/YbKb5xCEvtM=
gonum.org/v1/gonum v0.8.2/go.mod h1:oe/vMfY3deqTw+1EZJhuvEW2iwGF1bW9wwu7XCu0+v0=
gonum.org/v1/gonum v0.9.3/go.mod h1:TZumC3NeyVQskjXqmyWt4S3bINhy7B4eYwW69EbyX+0=
gonum.org/v1/gonum v0.15.0 h1:2lYxjRbTYyxkJxlhC+LvJIx3SsANPdRybu1tGj9/OrQ=
gonum.org/v1/gonum v0.15.0/go.mod h1:xzZVBJBtS+Mz4q0Yl2LJTk+OxOg4jiXZ7qBoM0uISGo=
gonum.org/v1/netlib v0.0.0-20190313105609-8cb42192e0e0 h1:OE9mWmgKkjJyEmDAAtGMPjXu+YNeGvK9VTSHY6+Qihc=
gonum.org/v1/netlib v0.0.0-20190313105609-8cb42192e0e0/go.mod h1:wa6Ws7BG/ESfp6dHfk7C6KdzKA7wR7u/rKwOGE66zvw=
gonum.org/v1/plot v0.0.0-20190515093506-e2840ee46a6b/go.mod h1:Wt8AAjI+ypCyYX3nZBvf6cAIx93T+c/OS2HFAYskSZc=
gonum.org/v1/plot v0.9.0/go.mod h1:3Pcqqmp6RHvJI72kgb8fThyUnav364FOsdDo2aGW5lY=
google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
google.golang.org/genproto v0.0.0-20200513103714-09dca8ec2884/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
google.golang.org/genproto v0.0.0-20210630183607-d20f26d13c79/go.mod h1:yiaVoXHpRzHGyxV3o4DktVWY4mSUErTKaeEOq6C3t3U=
google.golang.org/genproto v0.0.0-20200911024640-645f7a48b24f h1:Yv4xsIx7HZOoyUGSJ2ksDyWE2qIBXROsZKt2ny3hCGM=
google.golang.org/genproto v0.0.0-20200911024640-645f7a48b24f/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
google.golang.org/grpc v1.33.1/go.mod h1:fr5YgcSWrqhRRxogOsw7RzIpsmvOZ6IcH4kBYTpR3n0=
google.golang.org/grpc v1.36.0/go.mod h1:qjiiYl8FncCW8feJPdyg3v6XW24KsRHe+dy9BAGRRjU=
google.golang.org/grpc v1.38.0/go.mod h1:NREThFqKR1f3iQ6oBuvc5LadQuXVGo9rkm5ZGrQdJfM=
google.golang.org/grpc v1.39.0/go.mod h1:PImNr+rS9TWYb2O4/emRugxiyHZ5JyHW5F+RPnDzfrE=
google.golang.org/grpc v1.32.0 h1:zWTV+LMdc3kaiJMSTOFz2UgSBgx8RNQoTGiZu3fR9S0=
google.golang.org/grpc v1.32.0/go.mod h1:N36X2cJ7JwdamYAgDz+s+rVMFjt3numwzf/HckM8pak=
google.golang.org/grpc/cmd/protoc-gen-go-grpc v0.0.0-20200910201057-6591123024b3/go.mod h1:6Kw0yEErY5E/yWrBtf03jp27GLLJujG4z/JK95pnjjw=
google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
@@ -336,18 +283,20 @@ google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzi
google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
google.golang.org/protobuf v1.24.0/go.mod h1:r/3tXBNzIEhYS9I1OUVjXDlt8tc493IdKGjtUeSXeh4=
google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
google.golang.org/protobuf v1.34.1 h1:9ddQBjfCyZPOHPUiPxpYESBLc+T8P3E+Vo4IbKZgFWg=
google.golang.org/protobuf v1.34.1/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.3/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gorgonia.org/vecf32 v0.9.0 h1:PClazic1r+JVJ1dEzRXgeiVl4g1/Hf/w+wUSqnco1Xg=
@@ -356,5 +305,4 @@ gorgonia.org/vecf64 v0.9.0 h1:bgZDP5x0OzBF64PjMGC3EvTdOoMEcmfAh1VCUnZFm1A=
gorgonia.org/vecf64 v0.9.0/go.mod h1:hp7IOWCnRiVQKON73kkC/AUMtEXyf9kGlVrtPQ9ccVA=
honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

View File

@@ -217,7 +217,7 @@ func TestMultiModelStress(t *testing.T) {
defer wg.Done()
for j := 0; j < 3; j++ {
slog.Info("Starting", "req", i, "iter", j, "model", req[i].Model)
DoGenerate(ctx, t, client, req[i], resp[i], 120*time.Second, 5*time.Second)
DoGenerate(ctx, t, client, req[i], resp[i], 90*time.Second, 5*time.Second)
}
}(i)
}

View File

@@ -85,7 +85,7 @@ func GetTestEndpoint() (*api.Client, string) {
var serverMutex sync.Mutex
var serverReady bool
func startServer(t *testing.T, ctx context.Context, ollamaHost string) error {
func startServer(ctx context.Context, ollamaHost string) error {
// Make sure the server has been built
CLIName, err := filepath.Abs("../ollama")
if err != nil {
@@ -200,7 +200,7 @@ func InitServerConnection(ctx context.Context, t *testing.T) (*api.Client, strin
}
lifecycle.ServerLogFile = fp.Name()
fp.Close()
require.NoError(t, startServer(t, ctx, testEndpoint))
require.NoError(t, startServer(ctx, testEndpoint))
}
return client, testEndpoint, func() {

View File

@@ -329,10 +329,7 @@ func (llm GGML) GraphSize(context, batch uint64) (partialOffload, fullOffload ui
4*batch*(1+4*embedding+context+context*heads),
)
partialOffload = max(
4*batch*(2*embedding+vocab)+embedding*vocab*105/128,
4*batch*(2+3*embedding+context+context*heads),
)
partialOffload = 4*batch*(2*embedding+vocab) + embedding*vocab*105/128
case "stablelm":
fullOffload = 4 * batch * (context*(1+heads) + 3*embedding + 2)
partialOffload = max(

View File

@@ -12,8 +12,17 @@ import (
// This algorithm looks for a complete fit to determine if we need to unload other models
func PredictServerFit(allGpus gpu.GpuInfoList, ggml *GGML, adapters, projectors []string, opts api.Options) (bool, uint64) {
// Split up the GPUs by type and try them
var estimatedVRAM uint64
if opts.NumCtx > int(ggml.KV().ContextLength()) {
slog.Warn("requested context length is greater than model max context length", "requested", opts.NumCtx, "model", ggml.KV().ContextLength())
opts.NumCtx = int(ggml.KV().ContextLength())
}
if opts.NumCtx < 4 {
opts.NumCtx = 4
}
// Split up the GPUs by type and try them
for _, gpus := range allGpus.ByLibrary() {
var layerCount int
layerCount, estimatedVRAM, _ = EstimateGPULayers(gpus, ggml, projectors, opts)
@@ -53,12 +62,6 @@ func EstimateGPULayers(gpus []gpu.GpuInfo, ggml *GGML, projectors []string, opts
opts.NumCtx = max(opts.NumCtx, 2048)
}
layers := ggml.Tensors().Layers()
// add one layer worth of memory as a buffer
if blk0, ok := layers["blk.0"]; ok {
memoryMinimum += blk0.size()
}
// fp16 k,v = (1 (k) + 1 (v)) * sizeof(float16) * n_ctx * n_layer * n_embd / n_head * n_head_kv
var kv uint64 = 2 * 2 * uint64(opts.NumCtx) * ggml.KV().BlockCount() * ggml.KV().EmbeddingLength() / ggml.KV().HeadCount() * ggml.KV().HeadCountKV()
@@ -79,11 +82,13 @@ func EstimateGPULayers(gpus []gpu.GpuInfo, ggml *GGML, projectors []string, opts
graphPartialOffload = graphFullOffload
}
layers := ggml.Tensors().Layers()
// memoryRequiredTotal represents the memory required for full GPU offloading (all layers)
memoryRequiredTotal := memoryMinimum + graphFullOffload
memoryRequiredTotal := memoryMinimum + graphFullOffload + layers["blk.0"].size()
// memoryRequiredPartial represents the memory required for partial GPU offloading (n > 0, n < layers)
memoryRequiredPartial := memoryMinimum + graphPartialOffload
memoryRequiredPartial := memoryMinimum + graphPartialOffload + layers["blk.0"].size()
var memoryLayerOutput uint64
if layer, ok := layers["output_norm"]; ok {
@@ -104,17 +109,15 @@ func EstimateGPULayers(gpus []gpu.GpuInfo, ggml *GGML, projectors []string, opts
var layerCount int
for i := 0; i < int(ggml.KV().BlockCount()); i++ {
if blk, ok := layers[fmt.Sprintf("blk.%d", i)]; ok {
memoryLayer := blk.size()
memoryLayer := layers[fmt.Sprintf("blk.%d", i)].size()
// KV is proportional to the number of layers
memoryLayer += kv / ggml.KV().BlockCount()
// KV is proportional to the number of layers
memoryLayer += kv / ggml.KV().BlockCount()
memoryRequiredTotal += memoryLayer
if (opts.NumGPU >= 0 && layerCount+1 <= opts.NumGPU) || (opts.NumGPU < 0 && memoryAvailable > memoryRequiredPartial+memoryLayer) {
memoryRequiredPartial += memoryLayer
layerCount++
}
memoryRequiredTotal += memoryLayer
if memoryAvailable > memoryRequiredPartial+memoryLayer {
memoryRequiredPartial += memoryLayer
layerCount++
}
}
@@ -123,7 +126,7 @@ func EstimateGPULayers(gpus []gpu.GpuInfo, ggml *GGML, projectors []string, opts
memoryRequiredTotal += memoryLayerOutput
}
if (opts.NumGPU >= 0 && layerCount+1 <= opts.NumGPU) || (opts.NumGPU < 0 && memoryAvailable > memoryRequiredTotal) {
if memoryAvailable > memoryRequiredTotal {
layerCount = int(ggml.KV().BlockCount()) + 1
memoryRequiredPartial = memoryRequiredTotal
}
@@ -134,10 +137,10 @@ func EstimateGPULayers(gpus []gpu.GpuInfo, ggml *GGML, projectors []string, opts
"offload to gpu",
slog.Group(
"layers",
// requested number of layers to offload
"requested", opts.NumGPU,
// actual number of layers offloaded
"real", opts.NumGPU,
// estimated number of layers that can be offloaded
"real", layerCount,
"estimate", layerCount,
),
slog.Group(
"memory",

View File

@@ -38,7 +38,6 @@ type LlamaServer interface {
Detokenize(ctx context.Context, tokens []int) (string, error)
Close() error
EstimatedVRAM() uint64
EstimatedTotal() uint64
}
// llmServer is an instance of the llama.cpp server
@@ -78,7 +77,15 @@ func LoadModel(model string) (*GGML, error) {
// The gpu list must be a single family.
func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, projectors []string, opts api.Options) (LlamaServer, error) {
var err error
var cpuRunner string
if opts.NumCtx > int(ggml.KV().ContextLength()) {
slog.Warn("requested context length is greater than the model's training context window size", "requested", opts.NumCtx, "training size", ggml.KV().ContextLength())
}
if opts.NumCtx < 4 {
opts.NumCtx = 4
}
cpuRunner := ""
var estimatedVRAM uint64
var estimatedTotal uint64
var systemMemory uint64
@@ -89,7 +96,6 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
cpuRunner = serverForCpu()
gpuCount = 0
_, _, estimatedTotal = EstimateGPULayers(gpus, ggml, projectors, opts)
} else {
if gpus[0].Library == "metal" {
memInfo, err := gpu.GetCPUMem()
@@ -107,10 +113,6 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
// disable partial offloading when model is greater than total system memory as this
// can lead to locking up the system
opts.NumGPU = 0
} else if gpus[0].Library != "metal" && layers == 0 {
// Don't bother loading into the GPU if no layers can fit
cpuRunner = serverForCpu()
gpuCount = 0
} else if opts.NumGPU < 0 && layers > 0 && gpus[0].Library != "cpu" {
opts.NumGPU = layers
}
@@ -290,50 +292,30 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
done: make(chan error, 1),
}
s.cmd.Env = os.Environ()
s.cmd.Stdout = os.Stdout
s.cmd.Stderr = s.status
visibleDevicesEnv, visibleDevicesEnvVal := gpu.GpuInfoList(gpus).GetVisibleDevicesEnv()
pathEnvVal := strings.Join(libraryPaths, string(filepath.ListSeparator))
if v := strings.Join(libraryPaths, string(filepath.ListSeparator)); v != "" {
s.cmd.Env = append(s.cmd.Env, pathEnv+"="+v)
}
// Update or add the path and visible devices variable with our adjusted version
pathNeeded := true
devicesNeeded := visibleDevicesEnv != ""
for i := range s.cmd.Env {
cmp := strings.SplitN(s.cmd.Env[i], "=", 2)
if strings.EqualFold(cmp[0], pathEnv) {
s.cmd.Env[i] = pathEnv + "=" + pathEnvVal
pathNeeded = false
} else if devicesNeeded && strings.EqualFold(cmp[0], visibleDevicesEnv) {
s.cmd.Env[i] = visibleDevicesEnv + "=" + visibleDevicesEnvVal
devicesNeeded = false
if k, v := gpu.GpuInfoList(gpus).GetVisibleDevicesEnv(); k != "" {
s.cmd.Env = append(s.cmd.Env, k+"="+v)
}
for _, ev := range os.Environ() {
if strings.HasPrefix(ev, "CUDA_") ||
strings.HasPrefix(ev, "ROCM_") ||
strings.HasPrefix(ev, "HIP_") ||
strings.HasPrefix(ev, "HSA_") ||
strings.HasPrefix(ev, "GGML_") {
s.cmd.Env = append(s.cmd.Env, ev)
}
}
if pathNeeded {
s.cmd.Env = append(s.cmd.Env, pathEnv+"="+pathEnvVal)
}
if devicesNeeded {
s.cmd.Env = append(s.cmd.Env, visibleDevicesEnv+"="+visibleDevicesEnvVal)
}
slog.Info("starting llama server", "cmd", s.cmd.String())
if envconfig.Debug {
filteredEnv := []string{}
for _, ev := range s.cmd.Env {
if strings.HasPrefix(ev, "CUDA_") ||
strings.HasPrefix(ev, "ROCM_") ||
strings.HasPrefix(ev, "HIP_") ||
strings.HasPrefix(ev, "HSA_") ||
strings.HasPrefix(ev, "GGML_") ||
strings.HasPrefix(ev, "PATH=") ||
strings.HasPrefix(ev, "LD_LIBRARY_PATH=") {
filteredEnv = append(filteredEnv, ev)
}
}
// Log at debug as the environment is inherited and might contain sensitive information
slog.Debug("subprocess", "environment", filteredEnv)
}
// Log at debug as the environment is inherited and might contain sensitive information
slog.Debug("subprocess", "environment", s.cmd.Env)
if err = s.cmd.Start(); err != nil {
// Detect permission denied and augment them essage about noexec
@@ -971,10 +953,6 @@ func (s *llmServer) EstimatedVRAM() uint64 {
return s.estimatedVRAM
}
func (s *llmServer) EstimatedTotal() uint64 {
return s.estimatedTotal
}
func parseDurationMs(ms float64) time.Duration {
dur, err := time.ParseDuration(fmt.Sprintf("%fms", ms))
if err != nil {

View File

@@ -107,14 +107,9 @@ func toChatCompletion(id string, r api.ChatResponse) ChatCompletion {
Model: r.Model,
SystemFingerprint: "fp_ollama",
Choices: []Choice{{
Index: 0,
Message: Message{Role: r.Message.Role, Content: r.Message.Content},
FinishReason: func(reason string) *string {
if len(reason) > 0 {
return &reason
}
return nil
}(r.DoneReason),
Index: 0,
Message: Message{Role: r.Message.Role, Content: r.Message.Content},
FinishReason: &r.DoneReason,
}},
Usage: Usage{
// TODO: ollama returns 0 for prompt eval if the prompt was cached, but openai returns the actual count
@@ -132,16 +127,13 @@ func toChunk(id string, r api.ChatResponse) ChatCompletionChunk {
Created: time.Now().Unix(),
Model: r.Model,
SystemFingerprint: "fp_ollama",
Choices: []ChunkChoice{{
Index: 0,
Delta: Message{Role: "assistant", Content: r.Message.Content},
FinishReason: func(reason string) *string {
if len(reason) > 0 {
return &reason
}
return nil
}(r.DoneReason),
}},
Choices: []ChunkChoice{
{
Index: 0,
Delta: Message{Role: "assistant", Content: r.Message.Content},
FinishReason: &r.DoneReason,
},
},
}
}

View File

@@ -1,20 +1,20 @@
package envconfig
import (
"os"
"testing"
"github.com/stretchr/testify/require"
)
func TestConfig(t *testing.T) {
Debug = false // Reset whatever was loaded in init()
t.Setenv("OLLAMA_DEBUG", "")
os.Setenv("OLLAMA_DEBUG", "")
LoadConfig()
require.False(t, Debug)
t.Setenv("OLLAMA_DEBUG", "false")
os.Setenv("OLLAMA_DEBUG", "false")
LoadConfig()
require.False(t, Debug)
t.Setenv("OLLAMA_DEBUG", "1")
os.Setenv("OLLAMA_DEBUG", "1")
LoadConfig()
require.True(t, Debug)
}

View File

@@ -30,7 +30,6 @@ import (
"github.com/ollama/ollama/llm"
"github.com/ollama/ollama/openai"
"github.com/ollama/ollama/server/envconfig"
"github.com/ollama/ollama/types/errtypes"
"github.com/ollama/ollama/types/model"
"github.com/ollama/ollama/version"
)
@@ -408,6 +407,85 @@ func (s *Server) EmbeddingsHandler(c *gin.Context) {
c.JSON(http.StatusOK, resp)
}
func (s *Server) TokenizeHandler(c *gin.Context) {
var req api.TokenizeRequest
err := c.ShouldBindJSON(&req)
switch {
case errors.Is(err, io.EOF):
c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": "missing request body"})
return
case err != nil:
c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": err.Error()})
return
}
if req.Model == "" {
c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": "model is required"})
return
}
model, err := GetModel(req.Model)
if err != nil {
var pErr *fs.PathError
if errors.As(err, &pErr) {
c.JSON(http.StatusNotFound, gin.H{"error": fmt.Sprintf("model '%s' not found, try pulling it first", req.Model)})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
opts, err := modelOptions(model, req.Options)
if err != nil {
// TODO: handle specific errors
// if errors.Is(err, api.ErrInvalidOpts) {
// c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
// return
// }
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
var sessionDuration time.Duration
if req.KeepAlive == nil {
sessionDuration = getDefaultSessionDuration()
} else {
sessionDuration = req.KeepAlive.Duration
}
rCh, eCh := s.sched.GetRunner(c.Request.Context(), model, opts, sessionDuration)
var runner *runnerRef
select {
case runner = <-rCh:
case err = <-eCh:
if errors.Is(err, context.Canceled) {
c.JSON(499, gin.H{"error": "request canceled"})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
// an empty request loads the model
if req.Prompt == "" {
c.JSON(http.StatusOK, api.TokenizeResponse{Tokens: []int{}})
return
}
tokens, err := runner.llama.Tokenize(c.Request.Context(), req.Prompt)
if err != nil {
slog.Info(fmt.Sprintf("embedding generation failed: %v", err))
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to generate embedding"})
return
}
resp := api.TokenizeResponse{
Tokens: tokens,
}
c.JSON(http.StatusOK, resp)
}
func (s *Server) PullModelHandler(c *gin.Context) {
var req api.PullRequest
err := c.ShouldBindJSON(&req)
@@ -518,7 +596,7 @@ func (s *Server) CreateModelHandler(c *gin.Context) {
name := model.ParseName(cmp.Or(req.Model, req.Name))
if !name.IsValid() {
c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": errtypes.InvalidModelNameErrMsg})
c.AbortWithStatusJSON(http.StatusBadRequest, gin.H{"error": "invalid model name"})
return
}
@@ -555,12 +633,7 @@ func (s *Server) CreateModelHandler(c *gin.Context) {
ctx, cancel := context.WithCancel(c.Request.Context())
defer cancel()
quantization := req.Quantization
if req.Quantize != "" {
quantization = req.Quantize
}
if err := CreateModel(ctx, name.String(), filepath.Dir(req.Path), strings.ToUpper(quantization), modelfile, fn); err != nil {
if err := CreateModel(ctx, name.String(), filepath.Dir(req.Path), strings.ToUpper(req.Quantization), modelfile, fn); err != nil {
ch <- gin.H{"error": err.Error()}
}
}()
@@ -709,7 +782,7 @@ func GetModelInfo(req api.ShowRequest) (*api.ShowResponse, error) {
}
var sb strings.Builder
fmt.Fprintln(&sb, "# Modelfile generated by \"ollama show\"")
fmt.Fprintln(&sb, "# Modelfile generate by \"ollama show\"")
fmt.Fprintln(&sb, "# To build a new Modelfile based on this, replace FROM with:")
fmt.Fprintf(&sb, "# FROM %s\n\n", model.ShortName)
fmt.Fprint(&sb, model.String())
@@ -725,7 +798,7 @@ func (s *Server) ListModelsHandler(c *gin.Context) {
return
}
models := []api.ModelResponse{}
var models []api.ModelResponse
if err := filepath.Walk(manifests, func(path string, info os.FileInfo, _ error) error {
if !info.IsDir() {
rel, err := filepath.Rel(manifests, path)
@@ -973,6 +1046,7 @@ func (s *Server) GenerateRoutes() http.Handler {
r.POST("/api/generate", s.GenerateHandler)
r.POST("/api/chat", s.ChatHandler)
r.POST("/api/embeddings", s.EmbeddingsHandler)
r.POST("/api/tokenize", s.TokenizeHandler)
r.POST("/api/create", s.CreateModelHandler)
r.POST("/api/push", s.PushModelHandler)
r.POST("/api/copy", s.CopyModelHandler)
@@ -980,7 +1054,6 @@ func (s *Server) GenerateRoutes() http.Handler {
r.POST("/api/show", s.ShowModelHandler)
r.POST("/api/blobs/:digest", s.CreateBlobHandler)
r.HEAD("/api/blobs/:digest", s.HeadBlobHandler)
r.GET("/api/ps", s.ProcessHandler)
// Compatibility endpoints
r.POST("/v1/chat/completions", openai.Middleware(), s.ChatHandler)
@@ -1139,42 +1212,6 @@ func streamResponse(c *gin.Context, ch chan any) {
})
}
func (s *Server) ProcessHandler(c *gin.Context) {
models := []api.ModelResponse{}
for _, v := range s.sched.loaded {
model := v.model
modelDetails := api.ModelDetails{
Format: model.Config.ModelFormat,
Family: model.Config.ModelFamily,
Families: model.Config.ModelFamilies,
ParameterSize: model.Config.ModelType,
QuantizationLevel: model.Config.FileType,
}
mr := api.ModelResponse{
Model: model.ShortName,
Name: model.ShortName,
Size: int64(v.estimatedTotal),
SizeVRAM: int64(v.estimatedVRAM),
Digest: model.Digest,
Details: modelDetails,
ExpiresAt: v.expiresAt,
}
// The scheduler waits to set expiresAt, so if a model is loading it's
// possible that it will be set to the unix epoch. For those cases, just
// calculate the time w/ the sessionDuration instead.
var epoch time.Time
if v.expiresAt == epoch {
mr.ExpiresAt = time.Now().Add(v.sessionDuration)
}
models = append(models, mr)
}
c.JSON(http.StatusOK, api.ListResponse{Models: models})
}
// ChatPrompt builds up a prompt from a series of messages for the currently `loaded` model
func chatPrompt(ctx context.Context, runner *runnerRef, template string, messages []api.Message, numCtx int) (string, error) {
encode := func(s string) ([]int, error) {

View File

@@ -95,7 +95,6 @@ func Test_Routes(t *testing.T) {
err = json.Unmarshal(body, &modelList)
assert.Nil(t, err)
assert.NotNil(t, modelList.Models)
assert.Equal(t, 0, len(modelList.Models))
},
},

View File

@@ -6,7 +6,6 @@ import (
"fmt"
"log/slog"
"reflect"
"runtime"
"sort"
"strings"
"sync"
@@ -62,10 +61,6 @@ func InitScheduler(ctx context.Context) *Scheduler {
// context must be canceled to decrement ref count and release the runner
func (s *Scheduler) GetRunner(c context.Context, model *Model, opts api.Options, sessionDuration time.Duration) (chan *runnerRef, chan error) {
// allocate a large enough kv cache for all parallel requests
if opts.NumCtx < 4 {
opts.NumCtx = 4
}
opts.NumCtx = opts.NumCtx * envconfig.NumParallel
req := &LlmRequest{
@@ -178,7 +173,7 @@ func (s *Scheduler) processPending(ctx context.Context) {
}
// Trigger an expiration to unload once it's done
runnerToExpire.refMu.Lock()
slog.Debug("resetting model to expire immediately to make room", "modelPath", runnerToExpire.modelPath, "refCount", runnerToExpire.refCount)
slog.Debug("resetting model to expire immediately to make room", "model", runnerToExpire.model, "refCount", runnerToExpire.refCount)
if runnerToExpire.expireTimer != nil {
runnerToExpire.expireTimer.Stop()
runnerToExpire.expireTimer = nil
@@ -191,13 +186,13 @@ func (s *Scheduler) processPending(ctx context.Context) {
// Wait for the unload to happen
// Note: at this point we're queueing up all incoming requests, even if they were for
// a different model that's loaded and not scheduled to be removed.
slog.Debug("waiting for pending requests to complete and unload to occur", "modelPath", runnerToExpire.modelPath)
slog.Debug("waiting for pending requests to complete and unload to occur", "model", runnerToExpire.model)
select {
case <-ctx.Done():
slog.Debug("shutting down scheduler pending loop")
return
case <-s.unloadedCh:
slog.Debug("unload completed", "modelPath", runnerToExpire.modelPath)
slog.Debug("unload completed", "model", runnerToExpire.model)
continue
}
}
@@ -220,23 +215,23 @@ func (s *Scheduler) processCompleted(ctx context.Context) {
runner := s.loaded[finished.model.ModelPath]
s.loadedMu.Unlock()
if runner == nil {
slog.Error("finished requeset signal received after model unloaded", "modelPath", finished.model.ModelPath)
slog.Error("finished requeset signal received after model unloaded", "model", finished.model.ModelPath)
continue
}
runner.refMu.Lock()
runner.refCount--
if runner.refCount <= 0 {
if runner.sessionDuration <= 0 {
slog.Debug("runner with zero duration has gone idle, expiring to unload", "modelPath", runner.modelPath)
slog.Debug("runner with zero duration has gone idle, expiring to unload", "model", runner.model)
if runner.expireTimer != nil {
runner.expireTimer.Stop()
runner.expireTimer = nil
}
s.expiredCh <- runner
} else if runner.expireTimer == nil {
slog.Debug("runner with non-zero duration has gone idle, adding timer", "modelPath", runner.modelPath, "duration", runner.sessionDuration)
slog.Debug("runner with non-zero duration has gone idle, adding timer", "model", runner.model, "duration", runner.sessionDuration)
runner.expireTimer = time.AfterFunc(runner.sessionDuration, func() {
slog.Debug("timer expired, expiring to unload", "modelPath", runner.modelPath)
slog.Debug("timer expired, expiring to unload", "model", runner.model)
runner.refMu.Lock()
defer runner.refMu.Unlock()
if runner.expireTimer != nil {
@@ -245,21 +240,19 @@ func (s *Scheduler) processCompleted(ctx context.Context) {
}
s.expiredCh <- runner
})
runner.expiresAt = time.Now().Add(runner.sessionDuration)
} else {
slog.Debug("runner with non-zero duration has gone idle, resetting timer", "modelPath", runner.modelPath, "duration", runner.sessionDuration)
slog.Debug("runner with non-zero duration has gone idle, resetting timer", "model", runner.model, "duration", runner.sessionDuration)
runner.expireTimer.Reset(runner.sessionDuration)
runner.expiresAt = time.Now().Add(runner.sessionDuration)
}
}
slog.Debug("after processing request finished event", "modelPath", runner.modelPath, "refCount", runner.refCount)
slog.Debug("after processing request finished event", "model", runner.model, "refCount", runner.refCount)
runner.refMu.Unlock()
case runner := <-s.expiredCh:
slog.Debug("runner expired event received", "modelPath", runner.modelPath)
slog.Debug("runner expired event received", "model", runner.model)
runner.refMu.Lock()
if runner.refCount > 0 {
// Shouldn't happen, but safeguard to ensure no leaked runners
slog.Debug("expired event with positive ref count, retrying", "modelPath", runner.modelPath, "refCount", runner.refCount)
slog.Debug("expired event with positive ref count, retrying", "model", runner.model, "refCount", runner.refCount)
go func(runner *runnerRef) {
// We can't unload yet, but want to as soon as the current request completes
// So queue up another expired event
@@ -271,16 +264,16 @@ func (s *Scheduler) processCompleted(ctx context.Context) {
}
s.loadedMu.Lock()
slog.Debug("got lock to unload", "modelPath", runner.modelPath)
slog.Debug("got lock to unload", "model", runner.model)
finished := runner.waitForVRAMRecovery()
runner.unload()
delete(s.loaded, runner.modelPath)
delete(s.loaded, runner.model)
s.loadedMu.Unlock()
slog.Debug("runner released", "modelPath", runner.modelPath)
slog.Debug("runner released", "model", runner.model)
runner.refMu.Unlock()
<-finished
slog.Debug("sending an unloaded event", "modelPath", runner.modelPath)
slog.Debug("sending an unloaded event", "model", runner.model)
s.unloadedCh <- struct{}{}
}
}
@@ -319,20 +312,18 @@ func (s *Scheduler) load(req *LlmRequest, ggml *llm.GGML, gpus gpu.GpuInfoList)
req.errCh <- err
return
}
runner := &runnerRef{
model: req.model,
modelPath: req.model.ModelPath,
llama: llama,
Options: &req.opts,
sessionDuration: req.sessionDuration,
gpus: gpus,
estimatedVRAM: llama.EstimatedVRAM(),
estimatedTotal: llama.EstimatedTotal(),
loading: true,
refCount: 1,
}
runner := &runnerRef{}
runner.model = req.model.ModelPath
runner.adapters = req.model.AdapterPaths
runner.projectors = req.model.ProjectorPaths
runner.llama = llama
runner.Options = &req.opts
runner.sessionDuration = req.sessionDuration
runner.gpus = gpus
runner.estimatedVRAM = llama.EstimatedVRAM()
runner.loading = true
runner.refCount = 1
runner.refMu.Lock()
s.loadedMu.Lock()
s.loaded[req.model.ModelPath] = runner
slog.Info("loaded runners", "count", len(s.loaded))
@@ -344,7 +335,7 @@ func (s *Scheduler) load(req *LlmRequest, ggml *llm.GGML, gpus gpu.GpuInfoList)
slog.Error("error loading llama server", "error", err)
runner.refCount--
req.errCh <- err
slog.Debug("triggering expiration for failed load", "model", runner.modelPath)
slog.Debug("triggering expiration for failed load", "model", runner.model)
s.expiredCh <- runner
return
}
@@ -413,18 +404,17 @@ type runnerRef struct {
refCount uint // prevent unloading if > 0
// unloading bool // set to true when we are trying to unload the runner
llama llm.LlamaServer
loading bool // True only during initial load, then false forever
gpus gpu.GpuInfoList // Recorded at time of provisioning
estimatedVRAM uint64
estimatedTotal uint64
llama llm.LlamaServer
loading bool // True only during initial load, then false forever
gpus gpu.GpuInfoList // Recorded at time of provisioning
estimatedVRAM uint64
sessionDuration time.Duration
expireTimer *time.Timer
expiresAt time.Time
model *Model
modelPath string
model string
adapters []string
projectors []string
*api.Options
}
@@ -437,8 +427,9 @@ func (runner *runnerRef) unload() {
if runner.llama != nil {
runner.llama.Close()
}
runner.model = nil
runner.llama = nil
runner.adapters = nil
runner.projectors = nil
runner.Options = nil
runner.gpus = nil
}
@@ -467,8 +458,8 @@ func (runner *runnerRef) needsReload(ctx context.Context, req *LlmRequest) bool
ctx, cancel := context.WithTimeout(ctx, timeout)
defer cancel()
if !reflect.DeepEqual(runner.model.AdapterPaths, req.model.AdapterPaths) || // have the adapters changed?
!reflect.DeepEqual(runner.model.ProjectorPaths, req.model.ProjectorPaths) || // have the projectors changed?
if !reflect.DeepEqual(runner.adapters, req.model.AdapterPaths) || // have the adapters changed?
!reflect.DeepEqual(runner.projectors, req.model.ProjectorPaths) || // have the projectors changed?
!reflect.DeepEqual(optsExisting, optsNew) || // have the runner options changed?
runner.llama.Ping(ctx) != nil {
return true
@@ -488,8 +479,8 @@ func (runner *runnerRef) needsReload(ctx context.Context, req *LlmRequest) bool
func (runner *runnerRef) waitForVRAMRecovery() chan interface{} {
finished := make(chan interface{}, 1)
// CPU or Metal don't need checking, so no waiting required, windows can page VRAM, and the APIs we query tend to be optimistic on free space
if (len(runner.gpus) == 1 && (runner.gpus[0].Library == "cpu" || runner.gpus[0].Library == "metal")) || runtime.GOOS == "windows" {
// CPU or Metal don't need checking, so no waiting required
if len(runner.gpus) == 1 && (runner.gpus[0].Library == "cpu" || runner.gpus[0].Library == "metal") {
finished <- struct{}{}
return finished
}
@@ -572,9 +563,9 @@ func pickBestFitGPUs(req *LlmRequest, ggml *llm.GGML, gpus gpu.GpuInfoList) gpu.
// - try subsets of GPUs instead of just falling back to 1 or all in a family
// Now try all the GPUs
if ok, estimatedVRAM = llm.PredictServerFit(sgl, ggml, req.model.AdapterPaths, req.model.ProjectorPaths, req.opts); ok {
slog.Debug("new model will fit in available VRAM, loading", "model", req.model.ModelPath, "library", sgl[0].Library, "required", format.HumanBytes2(estimatedVRAM))
return sgl
if ok, estimatedVRAM = llm.PredictServerFit(gl, ggml, req.model.AdapterPaths, req.model.ProjectorPaths, req.opts); ok {
slog.Debug("new model will fit in available VRAM, loading", "model", req.model.ModelPath, "library", gl[0].Library, "required", format.HumanBytes2(estimatedVRAM))
return gl
}
}
return nil

View File

@@ -164,8 +164,7 @@ func TestRequests(t *testing.T) {
// simple reload of same model
scenario2a := newScenario(t, ctx, "ollama-model-1", 20)
tmpModel := *scenario1a.req.model
scenario2a.req.model = &tmpModel
scenario2a.req.model = scenario1a.req.model
scenario2a.ggml = scenario1a.ggml
// Multiple loaded models
@@ -497,9 +496,10 @@ func TestNeedsReload(t *testing.T) {
llm := &mockLlm{}
do := api.DefaultOptions()
runner := &runnerRef{
model: &Model{AdapterPaths: []string{"adapter1"}, ProjectorPaths: []string{"projector1"}},
Options: &do,
llama: llm,
adapters: []string{"adapter1"},
projectors: []string{"projector1"},
Options: &do,
llama: llm,
}
req := &LlmRequest{
model: &Model{
@@ -510,10 +510,10 @@ func TestNeedsReload(t *testing.T) {
}
resp := runner.needsReload(ctx, req)
require.True(t, resp)
req.model.AdapterPaths = runner.model.AdapterPaths
req.model.AdapterPaths = runner.adapters
resp = runner.needsReload(ctx, req)
require.True(t, resp)
req.model.ProjectorPaths = runner.model.ProjectorPaths
req.model.ProjectorPaths = runner.projectors
runner.loading = true
req.opts.NumBatch = 1234
resp = runner.needsReload(ctx, req)
@@ -558,11 +558,11 @@ func TestUnloadAllRunners(t *testing.T) {
func TestUnload(t *testing.T) {
llm1 := &mockLlm{}
r1 := &runnerRef{llama: llm1}
r2 := &runnerRef{model: &Model{AdapterPaths: []string{"A"}}}
r2 := &runnerRef{adapters: []string{"A"}}
r1.unload()
require.True(t, llm1.closeCalled)
r2.unload()
require.Nil(t, r2.model)
require.Nil(t, r2.adapters)
}
type mockLlm struct {
@@ -578,7 +578,6 @@ type mockLlm struct {
closeResp error
closeCalled bool
estimatedVRAM uint64
estimatedTotal uint64
}
func (s *mockLlm) Ping(ctx context.Context) error { return s.pingResp }
@@ -599,5 +598,4 @@ func (s *mockLlm) Close() error {
s.closeCalled = true
return s.closeResp
}
func (s *mockLlm) EstimatedVRAM() uint64 { return s.estimatedVRAM }
func (s *mockLlm) EstimatedTotal() uint64 { return s.estimatedTotal }
func (s *mockLlm) EstimatedVRAM() uint64 { return s.estimatedVRAM }

View File

@@ -7,7 +7,6 @@ import (
)
const UnknownOllamaKeyErrMsg = "unknown ollama key"
const InvalidModelNameErrMsg = "invalid model name"
// TODO: This should have a structured response from the API
type UnknownOllamaKey struct {

View File

@@ -291,9 +291,11 @@ func (n Name) Filepath() string {
panic("illegal attempt to get filepath of invalid name")
}
return filepath.Join(
n.Host,
n.Namespace,
n.Model,
strings.ToLower(filepath.Join(
n.Host,
n.Namespace,
n.Model,
)),
n.Tag,
)
}

View File

@@ -276,9 +276,9 @@ func TestFilepathAllocs(t *testing.T) {
allocs := testing.AllocsPerRun(1000, func() {
n.Filepath()
})
var allowedAllocs float64 = 1
var allowedAllocs float64 = 3
if runtime.GOOS == "windows" {
allowedAllocs = 3
allowedAllocs = 5
}
if allocs > allowedAllocs {
t.Errorf("allocs = %v; allowed %v", allocs, allowedAllocs)