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 (#5234)
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

Browse Source 
* fix mtp logprob bugs in chunk prefill

* merge code

* fix Request CONFLICT

* Revert "fix Request CONFLICT"

This reverts commit 7a438e4119.

* Revert "merge code"

This reverts commit 3839559b83.

* fix

* remove print

* fix

---------

Co-authored-by: sunlei1024 <sunlei5788@gmail.com>
This commit is contained in:
GoldPancake
2025-11-27 11:32:01 +08:00
committed by GitHub
parent cc588b70ab
commit bbcd92c8a0
5 changed files with 42 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/output/token_processor.py
View File

@@ -584,6 +584,8 @@ class TokenProcessor:
num_accepted_tokens = sum([x - 1 for x in real_accept_num])
self.num_accepted_tokens += num_accepted_tokens
num_emitted_tokens = sum(real_accept_num)
if num_emitted_tokens == 0:
return
self.num_emitted_tokens += num_emitted_tokens
main_process_metrics.spec_decode_num_accepted_tokens_total.inc(num_accepted_tokens)