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 }}
xLLM-AI
xllm
Repository navigation
Code
Issues
86
(86)
Pull requests
173
(173)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
16
(16)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
173
(173)
Closed
2,439
(2,439)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
Features/perf processor2
#2809
·
liutongxuan
opened
Nov 22, 2026
Collaborator
·
17 tasks
·
·
2
refactor: move algorithm logic into speculative worker implementations.
#2808
·
wai-bao
opened
Nov 21, 2026
Collaborator
·
·
feat: integrate dual affine LayerNorm on Ascend.
#2791
·
TreamTik
opened
Nov 19, 2026
·
9 of 11 tasks
·
·
5
feat: Add row and column INT8 quantization.
#2790
·
yuejiewang
opened
Nov 19, 2026
·
3 of 4 tasks
·
·
8
refactor: consolidate MTP draft registration and unify draft args config.
#2789
·
wai-bao
opened
Nov 19, 2026
Collaborator
·
·
1
perf: skip redundant rotary gathers in Qwen3-VL NPU decode.
#2782
·
imhaojie
opened
Nov 19, 2026
·
6 of 9 tasks
·
·
1
feat: add gr00t n1.7 inference on dcu.
#2780
·
theBlush
opened
Nov 18, 2026
·
13 of 16 tasks
·
·
11
bugfix: retain PD decode caches during schedule overlap.
#2778
·
wai-bao
opened
Nov 18, 2026
Collaborator
·
·
24
perf: add optional npu column-parallel weight layout.
#2772
·
Lilinchao11
opened
Nov 18, 2026
·
3 of 7 tasks
·
·
11
feat(npu): add packed page indices operator (Triton Ascend + native gather)
#2762
·
Hzhhh
opened
Nov 17, 2026
·
·
7
feat: Add packed page indices NPU operator.
#2761
·
Wzy-wm
opened
Nov 17, 2026
·
10 of 14 tasks
·
·
5
feat(npu): add PackedPageIndices task submission under xllm_ops
#2760
·
Fun10165
opened
Nov 17, 2026
·
5 tasks done
·
·
14
feat: Add token offset tile flags.
#2758
·
Wzy-wm
opened
Nov 17, 2026
·
10 of 17 tasks
·
·
12
Feat/dense block table translate
#2757
·
Wzy-wm
opened
Nov 17, 2026
·
·
4
feat: add automatic greedy output for qwen3.
#2751
·
xagr
opened
Nov 16, 2026
·
6 of 7 tasks
·
·
9
perf: select worker transport automatically by host.
#2749
·
liutongxuan
opened
Nov 15, 2026
Collaborator
·
17 tasks
·
·
4
refactor: unify causal VLMs into the causal-lm framework.
#2744
·
wai-bao
opened
Nov 14, 2026
Collaborator
·
·
1
feat: optimize MiniMax-H3 Ref2VA on 16 Ascend A3 NPUs
#2736
·
liuwenda4
opened
Nov 13, 2026
·
·
2
bugfix: support typed KV layouts and MLA graph execution.
#2731
·
xllm-org
opened
Nov 12, 2026
Collaborator
·
·
2
perf: prepare Qwen3-VL vision metadata on CPU.
#2720
·
xagr
opened
Nov 11, 2026
·
8 of 11 tasks
·
·
6
refactor: integrate npu normalization with kernel runtime.
#2711
·
XuZhang99
opened
Nov 11, 2026
Collaborator
·
4 of 6 tasks
·
·
4
perf: derive the decode graph batch ceiling from the speculative budget.
#2709
·
9wutong
opened
Nov 11, 2026
Contributor
·
10 of 17 tasks
·
·
11
bugfix: preflight MiniMax FP8 checkpoint indexes.
#2667
·
hswsplendid
opened
Nov 4, 2026
Contributor
·
8 of 17 tasks
·
·
4
bugfix: validate MiniMax FP8 dequantization inputs.
#2665
·
hswsplendid
opened
Nov 4, 2026
Contributor
·
8 of 17 tasks
·
·
3
feat: Add standalone T5 QKV append operator.
#2656
·
wangzhao-11a
opened
Nov 3, 2026
·
13 of 19 tasks
·
·
5
Previous
1
2
3
4
5
6
7
Next
You can’t perform that action at this time.