Skip to content

[CI][XPU] Add XPU chunked_prefill && prefix_caching case#5139

Merged
plusNew001 merged 1 commit intoPaddlePaddle:developfrom
plusNew001:xpu-ci-update
Nov 20, 2025
Merged

[CI][XPU] Add XPU chunked_prefill && prefix_caching case#5139
plusNew001 merged 1 commit intoPaddlePaddle:developfrom
plusNew001:xpu-ci-update

Conversation

@plusNew001
Copy link
Collaborator

Motivation

Modifications

Usage or Command

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.

Copilot AI review requested due to automatic review settings November 20, 2025 06:20
@paddle-bot
Copy link

paddle-bot bot commented Nov 20, 2025

Thanks for your contribution!

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds XPU testing coverage for chunked prefill and prefix caching features by enabling these flags in CI test scenarios.

  • Enables --enable-prefix-caching and --enable-chunked-prefill for the V1 model test (ERNIE-4.5-300B with wint4 quantization)
  • Enables --enable-chunked-prefill for the VL model test (ERNIE-4.5-VL-28B with wint8 quantization)

@plusNew001 plusNew001 merged commit c399475 into PaddlePaddle:develop Nov 20, 2025
20 of 22 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.

1 participant