Skip to content

[Speculative Decoding] split draft_tokens into standalone post-processing path #5230

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
sunlei1024 wants to merge 10 commits into from
Closed

[Speculative Decoding] split draft_tokens into standalone post-processing path #5230

sunlei1024 wants to merge 10 commits into from

Conversation

@sunlei1024
Copy link
Collaborator

@sunlei1024 sunlei1024 commented Nov 25, 2025

xunyoyo and others added 10 commits November 25, 2025 11:32
@xunyoyo
[CI] 【Hackathon 9th Sprint No.17】NO.17 功能模块单测补充 (PaddlePaddle#5054)
daf8b38 
* Refactor text processor tests to use unittest

* Add helpers for text processor tests
@xunyoyo
[CI] 【Hackathon 9th Sprint No.24】NO.24 功能模块单测补充 (PaddlePaddle#5055)
edf0d09 
* Add tp_utils tests

* Add header and tidy tp_utils test stubs
@freeliuzc
[Speculative Decoding][MTP]Update extract_mtp_weight script and optim…
5c8c2d4 
…ize config (PaddlePaddle#5183)

* update extract_mtp_model

* modify config usage
@plusNew001
[XPU] [CI] Xpu ci lock PaddlePaddle Version (PaddlePaddle#5218)
b9bdf82 
* Enhance run_ci_xpu.sh with caching and prefill options

* Update model path and configuration in run_ci_xpu.sh

* Add '北朝' keyword to assertion in run_45vl.py

* Enhance process termination logic in run_ci_xpu.sh

* Set timeout for CI_XPU job to 60 minutes

* Remove extra newline in stop_processes function

* Update paddlepaddle-xpu installation command

Comment out the previous paddlepaddle-xpu installation command and replace it with a specific version installation due to EP parallel error.
@liyonghua0910
[BugFix] fix work metrics not returned by metrics api (PaddlePaddle#4912
0937918 
)

* [BugFix] fix work metrics not returned by metrics api

* [fix] fix conflict

* [fix] fix ci
@kevincheng2 @Jiang-Jia-Jun
[BugFix] fix mm_positions type error (PaddlePaddle#5182)
df2be1c 
* fix mm_positions type error

* update code

* update code

* update code

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
@xiegegege
[benchmark]add qwen3-235b pd+ep yaml (PaddlePaddle#5225)
eae34a4
@EmmonsCurse
[CI] Add Cherry-Pick PR check logic (PaddlePaddle#5191)
e6b4b1f
@sunlei1024
refactor(mtp): split draft_tokens into standalone post-processing pat…
0ef5162 
…h for MTP + logprobs
@sunlei1024
Restore Request.__repr__ implementation
39888d4
@paddle-bot
Copy link

paddle-bot bot commented Nov 25, 2025

Thanks for your contribution!

@paddle-bot paddle-bot bot added the contributor External developers label Nov 25, 2025
@sunlei1024 sunlei1024 closed this Nov 25, 2025
@sunlei1024 sunlei1024 deleted the refac/mtp-cp-1131 branch November 25, 2025 14:07
@codecov-commenter
Copy link

codecov-commenter commented Nov 25, 2025

Codecov Report

❌ Patch coverage is 85.71429% with 7 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/online/20251131@a418d7b). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/__init__.py 71.42% 1 Missing and 1 partial ⚠️
fastdeploy/engine/request.py 71.42% 2 Missing ⚠️
fastdeploy/entrypoints/openai/serving_chat.py 33.33% 1 Missing and 1 partial ⚠️
fastdeploy/output/token_processor.py 96.87% 0 Missing and 1 partial ⚠️
Additional details and impacted files 
@@                    Coverage Diff                     @@
##             release/online/20251131    #5230   +/-   ##
==========================================================
  Coverage                           ?   59.10%           
==========================================================
  Files                              ?      317           
  Lines                              ?    38709           
  Branches                           ?     5819           
==========================================================
  Hits                               ?    22879           
  Misses                             ?    14014           
  Partials                           ?     1816
Flag Coverage Δ
GPU 59.10% <85.71%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

contributor External developers

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

9 participants

@sunlei1024 @codecov-commenter @xunyoyo @freeliuzc @plusNew001 @liyonghua0910 @kevincheng2 @xiegegege @EmmonsCurse