Skip to content

gemm block quantization infrastructure for llm decoder style#6814

Merged
nihui merged 43 commits into
Tencent:masterfrom
nihui:block-quantization-infrastructure
Jul 13, 2026
Merged

gemm block quantization infrastructure for llm decoder style#6814
nihui merged 43 commits into
Tencent:masterfrom
nihui:block-quantization-infrastructure

Conversation

@nihui

@nihui nihui commented Jul 8, 2026

Copy link
Copy Markdown
Member

No description provided.

nihui and others added 30 commits December 4, 2025 19:22
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
@tencent-adm

Copy link
Copy Markdown
Member

CLA assistant check
Thank you for your submission, we really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

@codecov-commenter

codecov-commenter commented Jul 8, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 87.95620% with 66 lines in your changes missing coverage. Please review.
✅ Project coverage is 95.12%. Comparing base (13b6d53) to head (be7bb5f).

Files with missing lines Patch % Lines
src/layer/multiheadattention.cpp 91.14% 27 Missing ⚠️
src/layer/gemm.cpp 84.33% 26 Missing ⚠️
src/layer/vulkan/multiheadattention_vulkan.cpp 36.36% 7 Missing ⚠️
src/layer/vulkan/gemm_vulkan.cpp 50.00% 6 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##           master    #6814      +/-   ##
==========================================
+ Coverage   94.70%   95.12%   +0.41%     
==========================================
  Files         947      947              
  Lines      415846   416292     +446     
==========================================
+ Hits       393844   395999    +2155     
+ Misses      22002    20293    -1709     

☔ View full report in Codecov by Harness.
📢 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.

@nihui nihui mentioned this pull request Jul 10, 2026
6 tasks
@github-actions

Copy link
Copy Markdown

Please enable github action in YOUR FORKED REPO to make code-format workflow work

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: be7bb5f3a8

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread tools/quantize/ncnnllm2table.cpp
@nihui
nihui merged commit f74639d into Tencent:master Jul 13, 2026
125 of 132 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants