Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
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
{{ message }}
intel
auto-round
Repository navigation
Code
Issues
58
(58)
Pull requests
40
(40)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
37
(37)
Milestones
4
(4)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
40
(40)
Closed
1,773
(1,773)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
Fix DeepSeek V4 model-free NVFP4 E5M3 layer overrides
#2658
·
changwangss
opened
Nov 19, 2026
Contributor
·
·
6
fix(nvfp4): prevent invalid global scales in MoE exports
#2657
·
lkk12014402
opened
Nov 19, 2026
Contributor
·
·
·
0.17.0
8
[model-free] Split fused-expert block-FP8 *_scale_inv and record real index total_size
#2656
·
XuehaoSun
opened
Nov 19, 2026
Contributor
·
4 tasks
·
·
5
fix(ark): support XPU graph capture for MoE GEMM
#2655
·
Zhenzhong1
opened
Nov 19, 2026
Contributor
·
3 tasks done
·
·
16
feat: support TR-HASH moe for tuned and model-free quantization
#2654
·
n1ck-guo
opened
Nov 19, 2026
Contributor
·
4 tasks
·
·
7
fix: update format handling in quantization configuration for model-free flow
#2653
·
xin3he
opened
Nov 19, 2026
Contributor
·
1 of 4 tasks
·
·
7
fix: don't substring-match org/name calibration datasets
#2651
·
0z5a
opened
Nov 18, 2026
Contributor
·
2 of 4 tasks
·
·
1
5
fix: enable DeepSeek V4 native FP4 requantization and preserve export names
#2649
·
changwangss
opened
Nov 18, 2026
Contributor
·
·
30
feat: introduce AR_NVFP_ACT_AMAX_ALPHA for scaling NVFP activation amax during calibration
#2647
·
xin3he
opened
Nov 18, 2026
Contributor
·
4 tasks
·
·
12
fix: apply the stored zero-point offset in the zp fused kernels
#2646
·
lxcxjxhx
opened
Nov 18, 2026
·
·
3
perf: run QuantLinearFunction on the fused triton kernels
#2645
·
lxcxjxhx
opened
Nov 18, 2026
·
·
4
fix: mask the packed tail in the transposed fused triton matmul
#2644
·
lxcxjxhx
opened
Nov 18, 2026
·
·
4
test: check the fused triton matmul against a plain-torch reference
#2643
·
lxcxjxhx
opened
Nov 18, 2026
·
·
3
fix: mask the K tail in the fused triton matmul
#2642
·
lxcxjxhx
opened
Nov 18, 2026
·
·
4
fix: wrap GPTQ's -1 group marker in the fused triton matmul
#2641
·
lxcxjxhx
opened
Nov 18, 2026
·
·
4
test: pin the two triton int2/4/8 matmul paths to the same result
#2640
·
lxcxjxhx
opened
Nov 18, 2026
·
·
1
fix: keep the triton autotuner from raising when two configs tie
#2639
·
lxcxjxhx
opened
Nov 18, 2026
·
·
3
docs: align two data-type docstrings with the signatures they document
#2638
·
lxcxjxhx
opened
Nov 18, 2026
·
·
5
refactor: decouple SVDQuant runtime exporters
#2637
·
changwangss
opened
Nov 17, 2026
Contributor
·
3 of 4 tasks
·
·
4
Support LLMC Format for Exported HMT Models
#2629
·
lkk12014402
opened
Nov 15, 2026
Contributor
·
4 tasks
·
·
8
fix(calib): support dataset config specs and recover from streaming schema errors (#2616)
#2628
·
Prajwal7-2002
opened
Nov 15, 2026
·
3 of 4 tasks
·
·
1
11
fix(rrq): address PR #2308 review feedback
#2626
·
luoyu-intel
opened
Nov 13, 2026
Contributor
·
·
12
feat(examples): add NVFP4 quantization recipe for dots.mocr
#2625
·
Jagadeeshwaran-J
opened
Nov 13, 2026
·
2 of 4 tasks
·
·
6
auto-scheme exp backup
draft
won't merge
#2613
·
WeiweiZhang1
opened
Nov 10, 2026
Contributor
·
4 tasks
·
·
6
add hessian for auto scheme
draft
WIP
#2612
·
n1ck-guo
opened
Nov 10, 2026
Contributor
·
4 tasks
·
·
11
Previous
1
2
Next
You can’t perform that action at this time.