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

[BugFix] fix mtp logprob bugs in chunk prefill (#5244)

Browse Source 
* fix mtp logprob bugs in chunk prefill

* fix

* fix
This commit is contained in:
GoldPancake
2025-11-27 11:31:29 +08:00
committed by GitHub
parent c424e08dc5
commit cfc5b0ccf9
5 changed files with 166 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/model_executor/pre_and_post_process.py
View File

@@ -514,8 +514,11 @@ def post_process_specualate(
sampler_output.token_num_per_batch,
sampler_output.cu_batch_token_offset,
model_output.not_need_stop,
model_output.seq_lens_decoder,
model_output.prompt_lens,
3, # mtype
model_output.mp_rank,
save_each_rank,
)
# Update pre_ids through accept tokens