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 }}
InternLM
lmdeploy
Repository navigation
Code
Issues
549
(549)
Pull requests
121
(121)
Discussions
Actions
Projects
Security and quality
8
(8)
Insights
More
items
All pull requests
Labels
34
(34)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
121
(121)
Closed
2,638
(2,638)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
Reduce Triton FlashAttention prefill shared memory usage on SM120
#5179
·
zzwwrr
opened
Nov 20, 2026
Collaborator
·
·
feat(moe): serve gpt-oss MXFP4 experts through the TurboMind channel
#5177
·
windreamer
opened
Nov 20, 2026
Collaborator
·
9/9
·
·
1
feat(quant): CT FP8 lanes on the TM channel — per-channel and 128-blocked
#5176
·
windreamer
opened
Nov 20, 2026
Collaborator
·
8/9
·
·
1
fix(kernel): index quantized paged attention by query token
#5175
·
YuvrajSinghBhadoria2
opened
Nov 19, 2026
·
·
1
2
feat(quant): NVFP4 lanes on the TM channel — SM80 family, native global scales (SM75–SM90)
#5173
·
windreamer
opened
Nov 19, 2026
Collaborator
·
7/9
·
·
1
feat: extend DCP to GQA and optimize query communication (rebased)
#5172
·
yidingcheng0206
opened
Nov 19, 2026
Collaborator
·
·
10
feat(graph): CUDA graph capture for the TurboMind grouped W4A16 MoE route
#5171
·
windreamer
opened
Nov 19, 2026
Collaborator
·
6/9
·
·
1
[Fix] Handle constant vectors in INT4/INT8 KV cache quantization
#5170
·
huihoudantuiren
opened
Nov 19, 2026
·
5 tasks done
·
·
1
1
feat(moe): expert-parallel fill-in for the TurboMind grouped W4A16 route
#5169
·
windreamer
opened
Nov 19, 2026
Collaborator
·
5/9
·
·
1
[Feature] Add GLM-5.3 vision operator candidates
#5168
·
qescccczmr
opened
Nov 19, 2026
Collaborator
·
·
3
fix: skip guided-token accept on non-final prefill chunks
#5167
·
wanfengcxz
opened
Nov 19, 2026
Collaborator
·
·
[Feature] Add GLM-5.3 KDA projection and head alignment
#5166
·
qescccczmr
opened
Nov 19, 2026
Collaborator
·
·
[Fix] Copy unrotated tail columns in apply_rotary_pos_emb for partial rotation
#5165
·
shotsan
opened
Nov 18, 2026
·
3 tasks done
·
·
1
[Fix] Count requests cancelled while waiting for a handle
#5164
·
RunningLeon
opened
Nov 18, 2026
Collaborator
·
2 tasks done
·
·
[Feature] Support GLM-5.3-Flash inference on Ascend NPU
#5163
·
wanfengcxz
opened
Nov 18, 2026
Collaborator
·
·
feat(moe): grouped W4A16 MoE via the TM GEMM channel
#5161
·
windreamer
opened
Nov 18, 2026
Collaborator
·
4/9
·
·
6
feat(gptq): load-time GPTQ repack onto the AWQ path
#5160
·
windreamer
opened
Nov 18, 2026
Collaborator
·
3/9
·
·
10
feat(w4a16): load-time compressed-tensors to AWQ normalization
#5159
·
windreamer
opened
Nov 18, 2026
Collaborator
·
2/9
·
·
9
feat(w4a16): graft TurboMind W4A16 GEMM into the PyTorch engine
#5158
·
windreamer
opened
Nov 18, 2026
Collaborator
·
1/9
·
·
8
fix: read and write text files as UTF-8
#5157
·
kodurd
opened
Nov 18, 2026
Contributor
·
·
test: make repetition penalty checks deterministic
#5153
·
silencelamb
opened
Nov 17, 2026
Collaborator
·
3 tasks done
·
·
[Fix] /v1/messages stop sequences vs thinking + thinking param validation
#5151
·
wanfengcxz
opened
Nov 17, 2026
Collaborator
·
·
2
fix(pytorch): preserve MoE routes in DP1 CUDA graphs
#5149
·
RunningLeon
opened
Nov 17, 2026
Collaborator
·
4 tasks done
·
·
1
fix(gpt-oss): render tools without a description
#5148
·
kodurd
opened
Nov 17, 2026
Contributor
·
·
feat(turbomind): MTP speculative decoding and SM75 verification attention
#5146
·
richardclli
opened
Nov 17, 2026
·
·
2
Previous
1
2
3
4
5
Next
You can’t perform that action at this time.