Skip to content

Conversation

@ckl117
Copy link
Collaborator

@ckl117 ckl117 commented Dec 10, 2025

Motivation

Qwen support dynamic block_wise_fp8 cache

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick,PR标题需遵循格式,在最开始加上[Cherry-Pick]标签,以及最后面加上原PR ID,例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

Modifications

Add append_decode_cache_T_int8_neox_rope_kernel

Usage or Command

python -m fastdeploy.entrypoints.openai.api_server \
    --model Qwen2-7B-Instruct \
    --tensor-parallel-size $1 \
    --port 8212 \
    --quantization '{"quantization":"mix_quant","kv_cache_quant_type":"block_wise_fp8"}'

Accuracy Tests

Checklist

  • Add at least a tag in the PR title.
    • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
    • You can add new tags based on the PR content, but the semantics must be clear.
  • Format your code, run pre-commit before commit.
  • Add unit tests. Please write the reason in this PR if no unit tests.
  • Provide accuracy results.
  • If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

@paddle-bot
Copy link

paddle-bot bot commented Dec 10, 2025

Thanks for your contribution!

@codecov-commenter
Copy link

codecov-commenter commented Dec 10, 2025

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@f32e331). Learn more about missing BASE report.

Additional details and impacted files
@@            Coverage Diff             @@
##             develop    #5486   +/-   ##
==========================================
  Coverage           ?   60.75%           
==========================================
  Files              ?      329           
  Lines              ?    41136           
  Branches           ?     6270           
==========================================
  Hits               ?    24991           
  Misses             ?    14254           
  Partials           ?     1891           
Flag Coverage Δ
GPU 60.75% <ø> (?)

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.

@ckl117 ckl117 changed the title qwen dynamic c8 rope [Feature][Optimization] Qwen Support Dynamic block_wise_fp8 cache Dec 12, 2025
@ckl117 ckl117 merged commit a389bb7 into PaddlePaddle:develop Dec 12, 2025
15 of 18 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants