apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] support min_p_sampling (#2872)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* Fastdeploy support min_p

* add test_min_p

* fix

* min_p_sampling

* update

* delete vl_gpu_model_runner.py

* fix

* Align usage of min_p with vLLM

* fix

* modified unit test

* fix test_min_sampling

* pre-commit all files

* fix

* fix

* fix

* fix xpu_model_runner.py
This commit is contained in:
lizexu123
2025-07-21 14:17:59 +08:00
committed by GitHub
parent 95a214ae43
commit 67990e0572
15 changed files with 302 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/model_executor/layers/sample/sampler.py
View File

@@ -30,6 +30,7 @@ from fastdeploy.model_executor.layers.sample.meta_data import SamplingMetadata
from fastdeploy.model_executor.layers.sample.ops import (
apply_penalty_multi_scores,
apply_speculative_penalty_multi_scores,
min_p_sampling,
top_k_top_p_sampling,
)
from fastdeploy.platforms import current_platform
@@ -266,6 +267,8 @@ class Sampler(nn.Layer):
probs = F.softmax(logits)
probs = min_p_sampling(probs, sampling_metadata.min_p)
_, next_tokens = top_k_top_p_sampling(probs, sampling_metadata.top_p, sampling_metadata.top_k)
logprobs_tensors = (
@@ -281,6 +284,7 @@ class Sampler(nn.Layer):
sampled_token_ids=next_tokens,
logprobs_tensors=logprobs_tensors,
)
return sampler_output