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

4
llama_toolchain/inference/api/endpoints.py
View file

@ -19,7 +19,6 @@ class CompletionRequest(BaseModel):
stream: Optional[bool] = False
logprobs: Optional[LogProbConfig] = None
quantization_config: Optional[QuantizationConfig] = None
@json_schema_type
@ -43,7 +42,6 @@ class BatchCompletionRequest(BaseModel):
content_batch: List[InterleavedTextAttachment]
sampling_params: Optional[SamplingParams] = SamplingParams()
logprobs: Optional[LogProbConfig] = None
quantization_config: Optional[QuantizationConfig] = None
@json_schema_type
@ -62,7 +60,6 @@ class ChatCompletionRequest(BaseModel):
stream: Optional[bool] = False
logprobs: Optional[LogProbConfig] = None
quantization_config: Optional[QuantizationConfig] = None
@json_schema_type
@ -88,7 +85,6 @@ class BatchChatCompletionRequest(BaseModel):
available_tools: Optional[List[ToolDefinition]] = Field(default_factory=list)
logprobs: Optional[LogProbConfig] = None
quantization_config: Optional[QuantizationConfig] = None
@json_schema_type