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/worker/gpu_model_runner.py
View File

@@ -320,6 +320,8 @@ class GPUModelRunner(ModelRunnerBase):
self.share_inputs["eos_token_id"][:] = np.array(request.eos_token_ids, dtype="int64").reshape(-1, 1)
self.share_inputs["top_p"][idx : idx + 1] = get_attr_from_request(request, "top_p", 0.7)
self.share_inputs["top_k"][idx : idx + 1] = request.get("top_k", 0)
self.share_inputs["min_p"][idx : idx + 1] = request.get("min_p", 0.0)
self.share_inputs["temperature"][idx : idx + 1] = get_attr_from_request(request, "temperature", 0.95)
self.share_inputs["penalty_score"][idx : idx + 1] = get_attr_from_request(
request, "repetition_penalty", 1.0
@@ -430,6 +432,7 @@ class GPUModelRunner(ModelRunnerBase):
self.share_inputs["eos_token_id"] = paddle.full([self.parallel_config.eos_tokens_lens, 1], 0, dtype="int64")
self.share_inputs["top_p"] = paddle.full([max_num_seqs, 1], self.model_config.top_p, dtype="float32")
self.share_inputs["top_k"] = paddle.full([max_num_seqs, 1], 0, dtype="int64")
self.share_inputs["min_p"] = paddle.full([max_num_seqs, 1], 0.0, dtype="float32")
self.share_inputs["temperature"] = paddle.full(
[max_num_seqs, 1], self.model_config.temperature, dtype="float32"
)
@@ -626,6 +629,7 @@ class GPUModelRunner(ModelRunnerBase):
temperature=self.share_inputs["temperature"],
top_p=self.share_inputs["top_p"],
top_k=self.share_inputs["top_k"],
min_p=self.share_inputs["min_p"],
step_idx=self.share_inputs["step_idx"],
pre_token_ids=self.share_inputs["pre_ids"],
prompt_ids=self.share_inputs["prompt_ids"],