Skip to content

[XPU][CI]Change W4A8 Case Base Value#5309

Merged
plusNew001 merged 1 commit intoPaddlePaddle:developfrom
plusNew001:ci-bug-fix
Dec 1, 2025
Merged

[XPU][CI]Change W4A8 Case Base Value#5309
plusNew001 merged 1 commit intoPaddlePaddle:developfrom
plusNew001:ci-bug-fix

Conversation

@plusNew001
Copy link
Collaborator

Motivation

💡 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

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 December 1, 2025 06:19
@paddle-bot
Copy link

paddle-bot bot commented Dec 1, 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 updates the XPU CI test for W4A8 quantization by expanding the acceptable response keywords in the assertion. The change adds "小度" (Xiaodu) as a valid keyword alongside the existing "人工智能" (artificial intelligence) and "文心一言" (ERNIE Bot) keywords when validating the model's self-introduction response.

Key Changes

  • Expanded the keyword validation list in the W4A8 quantization test to include "小度" as an acceptable model identity response

print(response.choices[0].message.content)
# print(base_response)
assert any(keyword in response.choices[0].message.content for keyword in ["人工智能", "文心一言"])
assert any(keyword in response.choices[0].message.content for keyword in ["人工智能", "文心一言", "小度"])
Copy link

Copilot AI Dec 1, 2025

Choose a reason for hiding this comment

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

此PR的描述信息不完整。虽然标题说明了要更改基准值,但PR描述中的"Motivation"和"Modifications"部分都是空的,没有解释为什么要添加"小度"作为可接受的关键词。

建议在PR描述中说明:

  1. Motivation: 为什么需要添加"小度"作为可接受的响应关键词?是因为模型响应行为发生了变化,还是为了支持新的模型版本?
  2. Modifications: 明确说明在w4a8量化测试中扩展了验证关键词列表,从["人工智能", "文心一言"]增加到["人工智能", "文心一言", "小度"]。
  3. Accuracy Tests: 如果这个改动影响了模型输出验证逻辑,请提供相关的测试结果或示例响应。

这样可以帮助审阅者理解修改的必要性和合理性。

Copilot generated this review using guidance from repository custom instructions.
@plusNew001 plusNew001 changed the title [XPU][CI]Change run_w4a8.py Base Value [XPU][CI]Change W4A8 Case Base Value Dec 1, 2025
@plusNew001 plusNew001 merged commit b467e9d into PaddlePaddle:develop Dec 1, 2025
18 of 22 checks passed
@codecov-commenter
Copy link

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@6f42c37). Learn more about missing BASE report.

Additional details and impacted files
@@            Coverage Diff             @@
##             develop    #5309   +/-   ##
==========================================
  Coverage           ?   59.77%           
==========================================
  Files              ?      324           
  Lines              ?    39598           
  Branches           ?     5954           
==========================================
  Hits               ?    23671           
  Misses             ?    14051           
  Partials           ?     1876           
Flag Coverage Δ
GPU 59.77% <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.

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.

2 participants