Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
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
Resources
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
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
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 }}
SemiAnalysisAI
InferenceX
Repository navigation
Code
Issues
102
(102)
Pull requests
231
(231)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
53
(53)
Milestones
5
(5)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
231
(231)
Closed
3,228
(3,228)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
fix(srt-slurm): bind discovery connector templates / 修复 discovery connector 模板绑定
#3895
·
YukioZzz
opened
Oct 10, 2026
Collaborator
·
5 of 11 tasks
·
·
5
[NVIDIA] GLM-5.2 NVFP4 B300 SGLang AgentX: tune EAGLE speculative steps / [NVIDIA] GLM-5.2 NVFP4 B300 SGLang AgentX:调优 EAGLE 推测步数
agentx
full-sweep-enabled
#3890
·
hshrivastava-droid
opened
Oct 9, 2026
Collaborator
·
4 of 7 tasks
·
·
2
refactor(agentx): stop aggregating server metrics in e2e
#3889
·
cquil11
opened
Oct 9, 2026
Collaborator
·
·
1
fix: pin huggingface-hub below 2 when installing lm-eval
#3886
·
cquil11
opened
Oct 9, 2026
Collaborator
·
·
1
chore: remove the standalone llm-d launcher
#3883
·
cquil11
opened
Oct 9, 2026
Collaborator
·
1/2
·
·
2
CollectiveX: run b300 EP16 over EFA with a faster aws-ofi-nccl / CollectiveX:在 EFA 上运行 b300 EP16 并使用更快的 aws-ofi-nccl
#3872
·
Oseltamivir
opened
Oct 9, 2026
Collaborator
·
·
1
[Klaud Cold] Update qwen3.5-fp8-h200-sglang-agentic-hicache-mtp SGLang image to v0.5.21-cu130 / [Klaud Cold] 将 qwen3.5-fp8-h200-sglang-agentic-hicache-mtp 的 SGLang 镜像更新至 v0.5.21-cu130
full-sweep-fail-fast
#3869
·
Klaud-Cold
opened
Oct 9, 2026
Collaborator
·
·
8
[Klaud Cold] Update DSR1 FP4 B300 SGLang image to v0.5.21 / [Klaud Cold] 将 DSR1 FP4 B300 SGLang 镜像更新至 v0.5.21
full-sweep-fail-fast
#3868
·
Klaud-Cold
opened
Oct 9, 2026
Collaborator
·
·
8
[Klaud Cold] Update DSR1 FP8 B300 SGLang image to v0.5.21 / [Klaud Cold] 将 DSR1 FP8 B300 SGLang 镜像更新至 v0.5.21
full-sweep-fail-fast
#3862
·
Klaud-Cold
opened
Oct 9, 2026
Collaborator
·
·
8
[AgentX] GB300 DSV4.1 Flash Dynamo-SGLang disagg: 2P TTL fix, fold, five more cells / [AgentX] GB300 DSV4.1 Flash Dynamo-SGLang 分离式:修复 2P 会话亲和 TTL、开启采样折叠、新增五个点
#3860
·
weireweire
opened
Oct 9, 2026
Collaborator
·
4 of 11 tasks
·
·
3
[AgentX] GB300 DSV4.1 Flash SGLang: 20261008 nightly, 16K chunks at TP4 c1 / [AgentX] GB300 DSV4.1 Flash SGLang:升级 20261008 nightly,TP4 c1 使用 16K chunk
#3859
·
weireweire
opened
Oct 9, 2026
Collaborator
·
4 of 11 tasks
·
·
1
[Klaud Cold] TEST: infx diff guidance comment, do not merge / [Klaud Cold] 测试:infx 行数评论说明,请勿合并
#3858
·
functionstackx
opened
Oct 9, 2026
Collaborator
·
·
1
chore(deps): bump multidict from 6.8.0 to 6.9.1 in /inferencex-e2e in the uv group across 1 directory
dependencies
python:uv
#3854
·
dependabot[bot]
opened
Oct 9, 2026
Bot
·
·
chore(amd): refresh GLM-5.2 MI355X AgentX to 20261008 daily / chore(amd): 更新 GLM-5.2 MI355X AgentX 20261008 daily 镜像
agentx
AMD
full-sweep-fail-fast
#3851
·
jiejingzhangamd
opened
Oct 9, 2026
Collaborator
·
·
3
[Klaud Cold] Update DSR1 FP8 B300 SGLang MTP image to v0.5.21 / [Klaud Cold] 将 DSR1 FP8 B300 SGLang MTP 镜像更新至 v0.5.21
full-sweep-fail-fast
#3847
·
Klaud-Cold
opened
Oct 9, 2026
Collaborator
·
·
8
[Klaud Cold] Update dsv41flash-fp4-b200-sglang-agentic-dspark SGLang image to nightly-dev-cu13-20261009-265efe5e / [Klaud Cold] 将 dsv41flash-fp4-b200-sglang-agentic-dspark 的 SGLang 镜像更新至 nightly-dev-cu13-20261009-265efe5e
full-sweep-fail-fast
#3846
·
Klaud-Cold
opened
Oct 9, 2026
Collaborator
·
·
8
[AMD][AgentX] DeepSeek V4.1 Flash MI325X vLLM NIXL frontier
non-canary-full-sweep-enabled
#3843
·
cquil11
opened
Oct 8, 2026
Collaborator
·
·
6
Compare MI300X vLLM NIXL AgentX configurations
non-canary-full-sweep-enabled
#3842
·
cquil11
opened
Oct 8, 2026
Collaborator
·
·
7
[NVIDIA][AgentX] GB300 GLM-5.2 NVFP4 Dynamo+SGLang aggregated: TP8 c1 and TP4 c4 retune / [NVIDIA][AgentX] GB300 GLM-5.2 NVFP4 Dynamo+SGLang 聚合配置:TP8 c1 与 TP4 c4 重新调优
agentx
full-sweep-enabled
#3838
·
hshrivastava-droid
opened
Oct 8, 2026
Collaborator
·
4 of 7 tasks
·
·
2
perf(dsv41flash): tune B200 vLLM AgentX DEP2/DEP4 and add TP2 c1 and DEP2 c128 host-KV rows / 调优 B200 vLLM AgentX DEP2/DEP4 并新增 TP2 c1 与 DEP2 c128 主机 KV 行
full-sweep-enabled
#3837
·
hshrivastava-droid
opened
Oct 8, 2026
Collaborator
·
6 of 11 tasks
·
·
3
Tune GLM-5.2 FP8 B300 SGLang AgentX recipes / 优化 GLM-5.2 FP8 B300 SGLang AgentX 配置
full-sweep-enabled
#3836
·
hshrivastava-droid
opened
Oct 8, 2026
Collaborator
·
3 of 7 tasks
·
·
10
[WIP]config: update B300 MiniMax-M3 TRT-LLM AgentX / 配置:更新 B300 MiniMax-M3 TRT-LLM AgentX
full-sweep-enabled
#3835
·
hshrivastava-droid
opened
Oct 8, 2026
Collaborator
·
3 of 11 tasks
·
·
4
[AMD][MI355X] Kimi-K3 vLLM AgentX nightly 81198e97 with dcp8 c1-c48 sweep / [AMD][MI355X] Kimi-K3 vLLM AgentX 更新镜像至 nightly 81198e97 并改为 dcp8 c1-c48 扫描
agentx
AMD
full-sweep-enabled
#3833
·
seungrokj
opened
Oct 8, 2026
Collaborator
·
·
8
Run DSv4 ATOM 1P1D c128/c256/c512 on EP8 Mega + LMCache MP / DSv4 ATOM 1P1D c128/c256/c512 改用 EP8 Mega + LMCache MP
full-sweep-enabled
#3831
·
yhl-amd
opened
Oct 8, 2026
Collaborator
·
·
2
[AMD][Qwen3.5] Update MI355X FP8 AgentX image to v0.5.21 and add TP8
full-sweep-fail-fast
#3830
·
yichiche
opened
Oct 8, 2026
Collaborator
·
·
2
Previous
1
2
3
4
5
6
7
…
10
Next
You can’t perform that action at this time.