FastDeploy

mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 17:17:14 +08:00

Files

chen 1e19833ba5 [CP] CP Lm head fp32 and temp_logprob to release/2.1 (#3766 )

* [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>

2025-09-01 19:56:54 +08:00

ernie4_5_vl

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

2025-09-01 19:56:54 +08:00

__init__.py

polish code with new pre-commit rule (#2923 )

2025-07-19 23:19:27 +08:00

deepseek_v3.py

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

2025-09-01 19:56:54 +08:00

ernie4_5_moe.py

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