mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 04:56:52 -04:00
* feat(vllm): expose AsyncEngineArgs via generic engine_args YAML map
LocalAI's vLLM backend wraps a small typed subset of vLLM's
AsyncEngineArgs (quantization, tensor_parallel_size, dtype, etc.).
Anything outside that subset -- pipeline/data/expert parallelism,
speculative_config, kv_transfer_config, all2all_backend, prefix
caching, chunked prefill, etc. -- requires a new protobuf field, a
Go struct field, an options.go line, and a backend.py mapping per
feature. That cadence is the bottleneck on shipping vLLM's
production feature set.
Add a generic `engine_args:` map on the model YAML that is
JSON-serialised into a new ModelOptions.EngineArgs proto field and
applied verbatim to AsyncEngineArgs at LoadModel time. Validation
is done by the Python backend via dataclasses.fields(); unknown
keys fail with the closest valid name as a hint.
dataclasses.replace() is used so vLLM's __post_init__ re-runs and
auto-converts dict values into nested config dataclasses
(CompilationConfig, AttentionConfig, ...). speculative_config and
kv_transfer_config flow through as dicts; vLLM converts them at
engine init.
Operators can now write:
engine_args:
data_parallel_size: 8
enable_expert_parallel: true
all2all_backend: deepep_low_latency
speculative_config:
method: deepseek_mtp
num_speculative_tokens: 3
kv_cache_dtype: fp8
without further proto/Go/Python plumbing per field.
Production defaults seeded by hooks_vllm.go: enable_prefix_caching
and enable_chunked_prefill default to true unless explicitly set.
Existing typed YAML fields (gpu_memory_utilization,
tensor_parallel_size, etc.) remain for back-compat; engine_args
overrides them when both are set.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(vllm): pin cublas13 to vLLM 0.20.0 cu130 wheel
vLLM's PyPI wheel is built against CUDA 12 (libcudart.so.12) and won't
load on a cu130 host. Switch the cublas13 build to vLLM's per-tag cu130
simple-index (https://wheels.vllm.ai/0.20.0/cu130/) and pin
vllm==0.20.0. The cu130-flavoured wheel ships libcudart.so.13 and
includes the DFlash speculative-decoding method that landed in 0.20.0.
cublas13 install gets --index-strategy=unsafe-best-match so uv consults
both the cu130 index and PyPI when resolving — PyPI also publishes
vllm==0.20.0, but with cu12 binaries that error at import time.
Verified: Qwen3.5-4B + z-lab/Qwen3.5-4B-DFlash loads and serves chat
completions on RTX 5070 Ti (sm_120, cu130).
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* ci(vllm): bot job to bump cublas13 vLLM wheel pin
vLLM's cu130 wheel index URL is itself version-locked
(wheels.vllm.ai/<TAG>/cu130/, no /latest/ alias upstream), so a vLLM
bump means rewriting two values atomically — the URL segment and the
version constraint. bump_deps.sh handles git-sha-in-Makefile only;
add a sibling bump_vllm_wheel.sh and a matching workflow job that
mirrors the existing matrix's PR-creation pattern.
The bumper queries /releases/latest (which excludes prereleases),
strips the leading 'v', and seds both lines unconditionally. When the
file is already on the latest tag the rewrite is a no-op and
peter-evans/create-pull-request opens no PR.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* docs(vllm): document engine_args and speculative decoding
The new engine_args: map plumbs arbitrary AsyncEngineArgs through to
vLLM, but the public docs only covered the basic typed fields. Add a
short subsection in the vLLM section explaining the typed/generic
split and showing a worked DFlash speculative-decoding config, with
pointers to vLLM's SpeculativeConfig reference and z-lab's drafter
collection.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
111 lines
2.9 KiB
Go
111 lines
2.9 KiB
Go
package config
|
|
|
|
import (
|
|
_ "embed"
|
|
"encoding/json"
|
|
"strings"
|
|
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
//go:embed parser_defaults.json
|
|
var parserDefaultsJSON []byte
|
|
|
|
type parserDefaultsData struct {
|
|
Families map[string]map[string]string `json:"families"`
|
|
Patterns []string `json:"patterns"`
|
|
}
|
|
|
|
var parsersData *parserDefaultsData
|
|
|
|
func init() {
|
|
parsersData = &parserDefaultsData{}
|
|
if err := json.Unmarshal(parserDefaultsJSON, parsersData); err != nil {
|
|
xlog.Warn("failed to parse parser_defaults.json", "error", err)
|
|
}
|
|
|
|
RegisterBackendHook("vllm", vllmDefaults)
|
|
RegisterBackendHook("vllm-omni", vllmDefaults)
|
|
}
|
|
|
|
// MatchParserDefaults returns parser defaults for the best-matching model family.
|
|
// Returns nil if no family matches. Used both at load time (via hook) and at import time.
|
|
func MatchParserDefaults(modelID string) map[string]string {
|
|
if parsersData == nil || len(parsersData.Patterns) == 0 {
|
|
return nil
|
|
}
|
|
normalized := normalizeModelID(modelID)
|
|
for _, pattern := range parsersData.Patterns {
|
|
if strings.Contains(normalized, pattern) {
|
|
if family, ok := parsersData.Families[pattern]; ok {
|
|
return family
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// productionEngineArgsDefaults are vLLM ≥ 0.6 features that production deployments
|
|
// almost always want. Applied at load time when the user hasn't set the key in
|
|
// engine_args. Anything user-supplied wins; we never silently override.
|
|
var productionEngineArgsDefaults = map[string]any{
|
|
"enable_prefix_caching": true,
|
|
"enable_chunked_prefill": true,
|
|
}
|
|
|
|
func vllmDefaults(cfg *ModelConfig, modelPath string) {
|
|
applyEngineArgDefaults(cfg)
|
|
applyParserDefaults(cfg)
|
|
}
|
|
|
|
// applyEngineArgDefaults seeds production-friendly engine_args without overwriting
|
|
// anything the user already set.
|
|
func applyEngineArgDefaults(cfg *ModelConfig) {
|
|
if cfg.EngineArgs == nil {
|
|
cfg.EngineArgs = map[string]any{}
|
|
}
|
|
for k, v := range productionEngineArgsDefaults {
|
|
if _, set := cfg.EngineArgs[k]; set {
|
|
continue
|
|
}
|
|
cfg.EngineArgs[k] = v
|
|
}
|
|
}
|
|
|
|
func applyParserDefaults(cfg *ModelConfig) {
|
|
hasToolParser := false
|
|
hasReasoningParser := false
|
|
for _, opt := range cfg.Options {
|
|
if strings.HasPrefix(opt, "tool_parser:") {
|
|
hasToolParser = true
|
|
}
|
|
if strings.HasPrefix(opt, "reasoning_parser:") {
|
|
hasReasoningParser = true
|
|
}
|
|
}
|
|
if hasToolParser && hasReasoningParser {
|
|
return
|
|
}
|
|
|
|
parsers := MatchParserDefaults(cfg.Model)
|
|
if parsers == nil {
|
|
parsers = MatchParserDefaults(cfg.Name)
|
|
}
|
|
if parsers == nil {
|
|
return
|
|
}
|
|
|
|
if !hasToolParser {
|
|
if tp, ok := parsers["tool_parser"]; ok {
|
|
cfg.Options = append(cfg.Options, "tool_parser:"+tp)
|
|
xlog.Debug("[parser_defaults] auto-set tool_parser", "parser", tp, "model", cfg.Model)
|
|
}
|
|
}
|
|
if !hasReasoningParser {
|
|
if rp, ok := parsers["reasoning_parser"]; ok {
|
|
cfg.Options = append(cfg.Options, "reasoning_parser:"+rp)
|
|
xlog.Debug("[parser_defaults] auto-set reasoning_parser", "parser", rp, "model", cfg.Model)
|
|
}
|
|
}
|
|
}
|