apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] support mtp logprob (#4464)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* support mtp logprob

* fix unitest
This commit is contained in:
GoldPancake
2025-10-20 15:18:12 +08:00
committed by GitHub
parent 1b9f351d21
commit 47595a2480
14 changed files with 1181 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/args_utils.py
View File

@@ -416,8 +416,6 @@ class EngineArgs:
# if self.dynamic_load_weight:
# self.enable_prefix_caching = False
if self.enable_logprob:
if self.speculative_config is not None:
raise NotImplementedError("Logprob does not support speculation_config.")
if not current_platform.is_cuda():
raise NotImplementedError("Only CUDA platform supports logprob.")
if self.speculative_config is not None: