phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Remove quantization_config from the APIs for now

Browse source
This commit is contained in:
Ashwin Bharambe 2024-08-21 14:17:05 -07:00
parent ab0a24f333
commit 863bb915e1
5 changed files with 18 additions and 157 deletions
Download patch file Download diff file Expand all files Collapse all files

112
rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.html
View file

@ -21,7 +21,7 @@
"info": {
"title": "[DRAFT] Llama Stack Specification",
"version": "0.0.1",
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-08-20 19:00:39.110138"
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-08-21 14:16:38.313950"
},
"servers": [
{
@ -1760,16 +1760,6 @@
}
},
"additionalProperties": false
},
"quantization_config": {
"oneOf": [
{
"$ref": "#/components/schemas/Bf16QuantizationConfig"
},
{
"$ref": "#/components/schemas/Fp8QuantizationConfig"
}
]
}
},
"additionalProperties": false,
@ -1778,19 +1768,6 @@
"messages_batch"
]
},
"Bf16QuantizationConfig": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "bf16"
}
},
"additionalProperties": false,
"required": [
"type"
]
},
"BuiltinTool": {
"type": "string",
"enum": [
@ -1848,19 +1825,6 @@
"tool_calls"
]
},
"Fp8QuantizationConfig": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "fp8"
}
},
"additionalProperties": false,
"required": [
"type"
]
},
"SamplingParams": {
"type": "object",
"properties": {
@ -2229,16 +2193,6 @@
}
},
"additionalProperties": false
},
"quantization_config": {
"oneOf": [
{
"$ref": "#/components/schemas/Bf16QuantizationConfig"
},
{
"$ref": "#/components/schemas/Fp8QuantizationConfig"
}
]
}
},
"additionalProperties": false,
@ -2307,16 +2261,6 @@
}
},
"additionalProperties": false
},
"quantization_config": {
"oneOf": [
{
"$ref": "#/components/schemas/Bf16QuantizationConfig"
},
{
"$ref": "#/components/schemas/Fp8QuantizationConfig"
}
]
}
},
"additionalProperties": false,
@ -2469,16 +2413,6 @@
}
},
"additionalProperties": false
},
"quantization_config": {
"oneOf": [
{
"$ref": "#/components/schemas/Bf16QuantizationConfig"
},
{
"$ref": "#/components/schemas/Fp8QuantizationConfig"
}
]
}
},
"additionalProperties": false,
@ -2552,16 +2486,6 @@
"$ref": "#/components/schemas/ShieldDefinition"
}
},
"quantization_config": {
"oneOf": [
{
"$ref": "#/components/schemas/Bf16QuantizationConfig"
},
{
"$ref": "#/components/schemas/Fp8QuantizationConfig"
}
]
},
"debug_prefix_messages": {
"type": "array",
"items": {
@ -4782,30 +4706,30 @@
{
"name": "RewardScoring"
},
{
"name": "AgenticSystem"
},
{
"name": "SyntheticDataGeneration"
},
{
"name": "Inference"
},
{
"name": "Datasets"
},
{
"name": "Observability"
},
{
"name": "AgenticSystem"
},
{
"name": "Inference"
},
{
"name": "Evaluations"
},
{
"name": "SyntheticDataGeneration"
},
{
"name": "PostTraining"
},
{
"name": "MemoryBanks"
},
{
"name": "Evaluations"
},
{
"name": "Attachment",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/Attachment\" />"
@ -4814,10 +4738,6 @@
"name": "BatchChatCompletionRequest",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/BatchChatCompletionRequest\" />"
},
{
"name": "Bf16QuantizationConfig",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/Bf16QuantizationConfig\" />"
},
{
"name": "BuiltinTool",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/BuiltinTool\" />"
@ -4826,10 +4746,6 @@
"name": "CompletionMessage",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/CompletionMessage\" />"
},
{
"name": "Fp8QuantizationConfig",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/Fp8QuantizationConfig\" />"
},
{
"name": "SamplingParams",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/SamplingParams\" />"
@ -5245,7 +5161,6 @@
"BatchChatCompletionResponse",
"BatchCompletionRequest",
"BatchCompletionResponse",
"Bf16QuantizationConfig",
"BuiltinShield",
"BuiltinTool",
"ChatCompletionRequest",
@ -5272,7 +5187,6 @@
"Experiment",
"ExperimentStatus",
"FinetuningAlgorithm",
"Fp8QuantizationConfig",
"InferenceStep",
"Log",
"LogMessagesRequest",