Skip to content

Navigation Menu

Appearance settings

View all features
- BY COMPANY SIZE
  Enterprises
  Small and medium teams
  Startups
  Nonprofits
- BY USE CASE
  App Modernization
  DevSecOps
  DevOps
  CI/CD
  View all use cases
- BY INDUSTRY
  Healthcare
  Financial services
  Manufacturing
  Government
  View all industries
View all solutions
- EXPLORE BY TOPIC
  AI
  Software Development
  DevOps
  Security
  View all topics
- EXPLORE BY TYPE
  Customer stories
  Events & webinars
  Ebooks & reports
  Business insights
  GitHub Skills
- SUPPORT & SERVICES
  Documentation
  Customer support
  Community forum
  Trust center
  Partners
View all resources
- COMMUNITY
  GitHub SponsorsFund open source developers
- PROGRAMS
  Security Lab
  Maintainer Community
  GitHub Stars
  Archive Program
- REPOSITORIES
  Topics
  Trending
  Collections
- ENTERPRISE SOLUTIONS
  Enterprise platformAI-powered developer platform
- AVAILABLE ADD-ONS
  GitHub Advanced SecurityEnterprise-grade security features
  Copilot for BusinessEnterprise-grade AI features
  Premium SupportEnterprise-grade 24/7 support
Pricing

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

microsoft / onnxruntime Public

Notifications You must be signed in to change notification settings
Fork 4.3k
Star 21.9k

Code
Issues 844
Pull requests 909
Discussions
Actions
Projects
Wiki
Security and quality
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security and quality
Insights

[CUDA] Add 2-bit MatMulNBits support - #32693

#32693

Merged

Tianlei Wu (tianleiwu) merged 3 commits into

microsoft:mainmicrosoft/onnxruntime:mainfrom

tianleiwu:tlwu/matmul-nbits-2bittianleiwu/onnxruntime:tlwu/matmul-nbits-2bitCopy head branch name to clipboard

Sep 21, 2026

Conversation Commits3 (3)Checks Files changed

Merged

[CUDA] Add 2-bit MatMulNBits support#32693
Tianlei Wu (tianleiwu) merged 3 commits into
microsoft:mainfrom
tianleiwu:tlwu/matmul-nbits-2bit

[CUDA] Add typed zero-point test coverage

c719cd4

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

Sign in for the full log view

Windows OpenVINO CI Pipeline on: pull_request 1

Windows OpenVINO CI Pipeline

windows_x64_release_xnnpack on: pull_request 1

build_x64_release_xnnpack

Linux CPU Minimal Build E2E on: pull_request 58

1. Build Full ORT and Generate ORT Files

2. Build Minimal (Exceptions Disabled)

4. Build Minimal (Globally Allowed Types)

5. Build Extended Minimal

6a. Build Regular (No Optional Features)

6b. Build Minimal (No Optional Features)

6c. Build Extended Minimal (No Optional Features)

3a. Build Minimal (Custom Ops)

3b. Build Minimal (Type Reduction)

7. Build Extended Minimal (Android NNAPI)

windows_x64_debug on: pull_request 2

build_x64_debug

ONNX Runtime WebGPU Builds on: pull_request 37

webgpu_build_x64_RelWithDebInfo (novcpkg, static)

webgpu_build_x64_RelWithDebInfo (vcpkg, static)

webgpu_plugin_build_x64_RelWithDebInfo

webgpu_external_dawn_build_x64_RelWithDebInfo

webgpu_minimal_build_edge_build_x64_RelWithDebInfo

PR Checks on: pull_request 5

Suggest fixes

Lint on: pull_request 9

Optional Lint

Python format

Optional Lint C++

WGSL Template Tests on: pull_request 1

WGSL Template Tests (ubuntu-latest)

WGSL Template Tests (windows-latest)

React Native CI Pipeline on: pull_request 7

Build Android AAR Packages

React Native CI iOS Build

React Native CI Android

React Native CI iOS E2E Tests

CodeQL on: pull_request 6

Analyze (java)

Analyze (javascript)

Analyze (python)

windows_x64_release_ep_generic_interface on: pull_request 1

build_x64_release_ep_generic_interface

ONNX Runtime CUDA Builds on: pull_request 2

Windows GPU CUDA CI Pipeline

Windows GPU CUDA CI Pipeline Test Job

Android CI on: pull_request 3

AndroidBinarySizeCheckJob_MinimalBaseline

android_nnapi_ep

Android CI Pipeline

Validate Gradle Wrapper on: pull_request

Validation

Windows CPU CI Pipeline on: pull_request 11

build_x86_release

windows_x64_asan on: pull_request 1

build_x64

CUDA Plugin Windows CI on: pull_request 2

Windows CUDA Plugin EP Build

Windows CUDA Plugin EP Test

Windows GPU TensorRT CI Pipeline on: pull_request 2

Windows GPU TensorRT CI Pipeline

Windows GPU TensorRT CI Pipeline Test Job

ONNX Runtime DirectML Builds on: pull_request 1

Windows GPU DML CI Pipeline

iOS_CI_on_Mac on: pull_request 2

iOS_CI_on_Mac

windows_x64_release on: pull_request 2

build_x64_release

Linux TensorRT CI on: pull_request 13

Build Linux TensorRT x64 Release / build_test_pipeline

Build Linux TensorRT CUDA Minimal x64 Release / build_test_pipeline

Test Linux TensorRT x64 Release

ONNX Runtime Windows GPU Doc Gen CI on: pull_request 13

Detect relevant changes

Windows GPU Kernel Documentation Build

Windows GPU Kernel Documentation Validation

windows_x64_release_vitisai on: pull_request 1

build_x64_release_vitisai

Linux CUDA CI on: pull_request 7

Build Linux CUDA x64 Release / build_test_pipeline

Test Linux CUDA x64 Release

Windows x64 QNN CI Pipeline on: pull_request 2

Windows x64 QNN CI Pipeline (shared_lib)

Windows x64 QNN CI Pipeline (static_lib)

CUDA Plugin Linux CI on: pull_request 6

Build Linux CUDA Plugin EP x64 Release / build_test_pipeline

Test Linux CUDA Plugin EP x64 Release

MacOS CI Pipeline on: pull_request 26

cpu / build-and-test (arm64, arm64, Debug)

cpu / build-and-test (arm64, arm64, Release)

cpu / build-and-test (arm64, arm64, Release, 16)

coreml / build-and-test (arm64, x86_64, Release)

coreml / build-and-test (arm64, arm64, Debug)

coreml / build-and-test (arm64, arm64, Release)

xnnpack / build-and-test (arm64, arm64, Debug)

webgpu / build-and-test (arm64, x86_64, Release)

webgpu / build-and-test (arm64, arm64, Debug)

webgpu / build-and-test (arm64, arm64, Release)

iphone_simulator (x86_64)

iphone_simulator (arm64)

Objective-C-StaticAnalysis

Linux OpenVINO CI on: pull_request 4

Build and Test OpenVINO EP (AlamLinux8, Py3.12) / build_test_pipeline

Linux WebGPU CI on: pull_request 5

Build Linux WebGPU x64 Release / build_test_pipeline

Linux CI on: pull_request 38

Build Linux x64 Debug (ASan) / build_test_pipeline

Build Linux x64 Release / build_test_pipeline

Build Linux x64 Release (Python 3.14) / build_test_pipeline

Build Linux x64 Release with training / build_test_pipeline

Build Linux arm64 Debug / build_test_pipeline

Build Linux arm64 Release / build_test_pipeline

Web CI Pipeline on: pull_request 7

precheck

wasm_Debug / build-wasm

wasm_Release / build-wasm

wasm_Release_static_library / build-wasm

web_Debug / build_onnxruntime_web

web_Release / build_onnxruntime_web

Microsoft GitHub Policy Service

license/cla

Code scanning results

CodeQL

lintrunner

Annotations

1 warning

Complete job

Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: microsoft/onnxruntime-github-actions/setup-build-tools@d19341fb036c43a947a2c0e4a53ad4d15e10bc5c. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/

Windows OpenVINO CI Pipeline

succeeded Sep 19, 2026 in 21m 28s

Loading

Re-running jobs...

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.