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
Public
Notifications
You must be signed in to change notification settings
Fork
315
Star
1.8k
Code
Issues
106
Pull requests
196
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
All pull requests
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
196
(196)
Closed
3,075
(3,075)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
More items
Comfortable display density
Compact display density
[AMD][MI355X] Enable INT4 quick reduce for DSv4.1 Flash on the latest ROCm 10 nightly / [AMD][MI355X] 在最新 ROCm 10 nightly 上为 DSv4.1 Flash 启用 INT4 quick reduce
full-sweep-enabled
#3697
·
Fangzhou-Ai
opened
Oct 3, 2026
Collaborator
·
·
6
[AMD][MI35X] 1003 DSV41 sglang mtp agentic
agentx
AMD
full-sweep-enabled
#3696
·
1am9trash
opened
Oct 3, 2026
Collaborator
·
·
3
Update GB200 DSV41flash vLLM image and retune TP4/DEP2/DEP4 / 更新 GB200 DSV41flash vLLM 镜像并调优 TP4/DEP2/DEP4
agentx
full-sweep-enabled
#3692
·
Juntian777
opened
Oct 3, 2026
Collaborator
·
7 of 11 tasks
·
·
4
[PowerX] accept native temperature artifacts / 兼容原生温度产物
#3685
·
edwingao28
opened
Oct 2, 2026
Collaborator
·
5 of 11 tasks
·
·
1
[PowerX] retire client-side GPU sampling / [PowerX] 移除客户端 GPU 功耗采样
#3684
·
edwingao28
opened
Oct 2, 2026
Collaborator
·
5 of 11 tasks
·
·
5
fix(kimik3): set MC_ENABLE_DEST_DEVICE_AFFINITY on GB300 agg Mooncake recipes / fix(kimik3):为 GB300 聚合 Mooncake 配方设置 MC_ENABLE_DEST_DEVICE_AFFINITY
#3683
·
redhairdragon
opened
Oct 2, 2026
·
6 of 11 tasks
·
·
[DNM] Test TokenSpeed with Dynamo and SMG through srt-slurm
#3679
·
cquil11
opened
Oct 2, 2026
Collaborator
·
·
1
Generalize sign-off verifier rules: config parity, run integrity, curve regressions / 签核验证规则通用化
#3678
·
adibarra
opened
Oct 2, 2026
Collaborator
·
·
Use srt-recipe for all SRT configs
#3677
·
cquil11
opened
Oct 2, 2026
Collaborator
·
·
2
chore: remove unused benchmark code
#3675
·
cquil11
opened
Oct 2, 2026
Collaborator
·
1/2
·
·
1
[Klaud Cold] Update qwen3.5-fp8-gb200-dynamo-sglang-mtp SGLang image to v0.5.21-cu130 / [Klaud Cold] 将 qwen3.5-fp8-gb200-dynamo-sglang-mtp 的 SGLang 镜像更新至 v0.5.21-cu130
full-sweep-fail-fast
#3672
·
Klaud-Cold
opened
Oct 2, 2026
Collaborator
·
·
4
[PowerX] collect NVL72 power by default / [PowerX] 默认采集 NVL72 功耗
#3670
·
edwingao28
opened
Oct 2, 2026
Collaborator
·
8 of 11 tasks
·
·
4
[DNM] Test SMG with SGLang, vLLM, and TRT-LLM through srt-slurm
#3665
·
cquil11
opened
Oct 2, 2026
Collaborator
·
·
1
[AMD][AGENTX] Tune dsv4 disagg umbp on Mi355X
agentx
AMD
full-sweep-fail-fast
#3664
·
billishyahao
opened
Oct 2, 2026
Collaborator
·
·
5
GLM-5.2 NVFP4 GB300 SGLang AgentX: MTP 5-1-6 aggregate, drop no-op settings / GB300 GLM-5.2 NVFP4 SGLang AgentX:聚合 MTP 5-1-6、删除无效设置
full-sweep-fail-fast
#3659
·
nvpohanh
opened
Oct 2, 2026
Collaborator
·
5 of 11 tasks
·
·
2
Add GLM-5.3 FP8 SGLang AgentX on MI300X with MoRI and UMBP
all-evals
full-sweep-enabled
#3657
·
cquil11
opened
Oct 2, 2026
Collaborator
·
·
4
Add GLM-5.3 MI325X AgentX with MORI and UMBP
all-evals
full-sweep-enabled
#3656
·
cquil11
opened
Oct 2, 2026
Collaborator
·
·
4
fix(klaud): defer unrunnable baseline rosters / 延后无法运行的基线候选
#3643
·
adibarra
opened
Oct 1, 2026
Collaborator
·
·
Single-node vLLM op-attribution profiling: per-kernel op/module, clocks, MoE routing
#3639
·
hbarclay
opened
Oct 1, 2026
Collaborator
·
·
[AMD][MI355X] Kimi-K3 MXFP4 vLLM: bump image to nightly-rocm100-ac9126e / Kimi-K3 MXFP4 vLLM:镜像升级至 nightly-rocm100-ac9126e
agentx
AMD
full-sweep-enabled
#3635
·
seungrokj
opened
Oct 1, 2026
Collaborator
·
1 task
·
·
4
[PowerX] Kimi-K3 B300 AgentX measured-power coverage
#3632
·
edwingao28
opened
Oct 1, 2026
Collaborator
·
7 of 10 tasks
·
·
1
Add B300 Dynamo+SGLang AgentX configs for DeepSeek V4 with aggregate DEP8 c384 / 添加含聚合式 DEP8 c384 的 DeepSeek V4 B300 Dynamo+SGLang AgentX 配置
full-sweep-fail-fast
#3631
·
nvpohanh
opened
Oct 1, 2026
Collaborator
·
·
8
feat(agentx): refresh DSV4 GB300 SGLang configs without W4A4 MegaMoE / 更新 DSV4 GB300 SGLang 配置并移除 W4A4 MegaMoE
full-sweep-fail-fast
#3630
·
nvpohanh
opened
Oct 1, 2026
Collaborator
·
·
6
[PowerX] MiniMax-M3 B200 AgentX measured-power coverage
full-sweep-fail-fast
#3628
·
edwingao28
opened
Oct 1, 2026
Collaborator
·
6 of 10 tasks
·
·
5
[AMD][MI355X] Kimi-K3 vLLM AgentX FP8 per-channel linear quantization-config / [AMD][MI355X] Kimi-K3 vLLM AgentX 新增 FP8 per-channel linear quantization-config
agentx
AMD
full-sweep-enabled
#3627
·
seungrokj
opened
Oct 1, 2026
Collaborator
·
·
2
Previous
1
2
3
4
5
6
7
8
Next
You can’t perform that action at this time.