apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[CP] CP Lm head fp32 and temp_logprob to release/2.1 (#3766)

Browse Source 
* [Feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing (#3552)

* [feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing

* infer engine support temp_scaled_logprobs and top_p_normalized_logprobs

* delete some code

* code check

* code check and add doc

* fix tokenizer.decoder(-1), return 'Invalid Token'

* add ci for temp_scaled and top_p logprobs

* check test

* check seq len time shape

* logprob clip inf

---------

Co-authored-by: sunlei1024 <sunlei5788@gmail.com>

* [Precision] Support lm_head layer running in float32 (#3597)

* support lm_head fp32 bf16 fp16

* support lm_head fp32 bf16 fp16

* add doc and check code

* lm_head_fp32 specify lm_head as fp32

* code check

* check doc

* code check

---------

Co-authored-by: sunlei1024 <sunlei5788@gmail.com>
This commit is contained in:
chen
2025-09-01 19:56:54 +08:00
committed by GitHub
parent 4da603daec
commit 1e19833ba5
22 changed files with 188 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
fastdeploy/entrypoints/openai/protocol.py
View File

@@ -371,6 +371,9 @@ class CompletionRequest(BaseModel):
echo: Optional[bool] = False
frequency_penalty: Optional[float] = None
logprobs: Optional[int] = None
# For logits and logprobs post processing
temp_scaled_logprobs: bool = False
top_p_normalized_logprobs: bool = False
max_tokens: Optional[int] = None
n: int = 1
presence_penalty: Optional[float] = None
@@ -502,6 +505,11 @@ class ChatCompletionRequest(BaseModel):
frequency_penalty: Optional[float] = None
logprobs: Optional[bool] = False
top_logprobs: Optional[int] = 0
# For logits and logprobs post processing
temp_scaled_logprobs: bool = False
top_p_normalized_logprobs: bool = False
# remove max_tokens when field is removed from OpenAI API
max_tokens: Optional[int] = Field(
default=None,
@@ -558,6 +566,8 @@ class ChatCompletionRequest(BaseModel):
req_dict["max_tokens"] = self.max_completion_tokens or self.max_tokens
req_dict["logprobs"] = self.top_logprobs if self.logprobs else None
req_dict["temp_scaled_logprobs"] = self.temp_scaled_logprobs
req_dict["top_p_normalized_logprobs"] = self.top_p_normalized_logprobs
# parse request model into dict, priority: request params > metadata params
if self.metadata is not None: