mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-25 01:02:05 -04:00
feat(swagger): update swagger (#9699)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
This commit is contained in:
@@ -919,7 +919,7 @@ const docTemplate = `{
|
||||
},
|
||||
"/api/models/vram-estimate": {
|
||||
"post": {
|
||||
"description": "Estimates VRAM based on model weight files, context size, and GPU layers",
|
||||
"description": "Estimates VRAM based on model weight files at multiple context sizes",
|
||||
"consumes": [
|
||||
"application/json"
|
||||
],
|
||||
@@ -3436,26 +3436,25 @@ const docTemplate = `{
|
||||
"modeladmin.VRAMResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"context_length": {
|
||||
"type": "integer"
|
||||
},
|
||||
"context_note": {
|
||||
"type": "string"
|
||||
},
|
||||
"model_max_context": {
|
||||
"type": "integer"
|
||||
},
|
||||
"sizeBytes": {
|
||||
"description": "total model weight size in bytes",
|
||||
"size_bytes": {
|
||||
"type": "integer"
|
||||
},
|
||||
"sizeDisplay": {
|
||||
"description": "human-readable size (e.g. \"4.2 GB\")",
|
||||
"size_display": {
|
||||
"type": "string"
|
||||
},
|
||||
"vramBytes": {
|
||||
"description": "estimated VRAM usage in bytes",
|
||||
"vram_bytes": {
|
||||
"type": "integer"
|
||||
},
|
||||
"vramDisplay": {
|
||||
"description": "human-readable VRAM (e.g. \"6.1 GB\")",
|
||||
"vram_display": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -916,7 +916,7 @@
|
||||
},
|
||||
"/api/models/vram-estimate": {
|
||||
"post": {
|
||||
"description": "Estimates VRAM based on model weight files, context size, and GPU layers",
|
||||
"description": "Estimates VRAM based on model weight files at multiple context sizes",
|
||||
"consumes": [
|
||||
"application/json"
|
||||
],
|
||||
@@ -3433,26 +3433,25 @@
|
||||
"modeladmin.VRAMResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"context_length": {
|
||||
"type": "integer"
|
||||
},
|
||||
"context_note": {
|
||||
"type": "string"
|
||||
},
|
||||
"model_max_context": {
|
||||
"type": "integer"
|
||||
},
|
||||
"sizeBytes": {
|
||||
"description": "total model weight size in bytes",
|
||||
"size_bytes": {
|
||||
"type": "integer"
|
||||
},
|
||||
"sizeDisplay": {
|
||||
"description": "human-readable size (e.g. \"4.2 GB\")",
|
||||
"size_display": {
|
||||
"type": "string"
|
||||
},
|
||||
"vramBytes": {
|
||||
"description": "estimated VRAM usage in bytes",
|
||||
"vram_bytes": {
|
||||
"type": "integer"
|
||||
},
|
||||
"vramDisplay": {
|
||||
"description": "human-readable VRAM (e.g. \"6.1 GB\")",
|
||||
"vram_display": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -349,21 +349,19 @@ definitions:
|
||||
type: object
|
||||
modeladmin.VRAMResponse:
|
||||
properties:
|
||||
context_length:
|
||||
type: integer
|
||||
context_note:
|
||||
type: string
|
||||
model_max_context:
|
||||
type: integer
|
||||
sizeBytes:
|
||||
description: total model weight size in bytes
|
||||
size_bytes:
|
||||
type: integer
|
||||
sizeDisplay:
|
||||
description: human-readable size (e.g. "4.2 GB")
|
||||
size_display:
|
||||
type: string
|
||||
vramBytes:
|
||||
description: estimated VRAM usage in bytes
|
||||
vram_bytes:
|
||||
type: integer
|
||||
vramDisplay:
|
||||
description: human-readable VRAM (e.g. "6.1 GB")
|
||||
vram_display:
|
||||
type: string
|
||||
type: object
|
||||
proto.MemoryUsageData:
|
||||
@@ -2820,8 +2818,8 @@ paths:
|
||||
post:
|
||||
consumes:
|
||||
- application/json
|
||||
description: Estimates VRAM based on model weight files, context size, and GPU
|
||||
layers
|
||||
description: Estimates VRAM based on model weight files at multiple context
|
||||
sizes
|
||||
parameters:
|
||||
- description: VRAM estimation parameters
|
||||
in: body
|
||||
|
||||
Reference in New Issue
Block a user