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 }}
SemiAnalysisAI
InferenceX
Repository navigation
Code
Issues
8
(8)
Pull requests
156
(156)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
64
(64)
Milestones
5
(5)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
156
(156)
Closed
4,482
(4,482)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
docs: schedule Qwen3.5 deprecation for November 26 / docs: 将 Qwen3.5 弃用日期定为 11 月 26 日
#5104
·
functionstackx
opened
Nov 16, 2026
Collaborator
·
·
feat(config): add TokenSpeed Muse Spark Open MXFP4 MI355X AgentX with decode monokernels / feat(config): 新增 TokenSpeed Muse Spark Open MXFP4 MI355X AgentX(decode monokernel)配置
full-sweep-enabled
#5103
·
bangtianliu
opened
Nov 16, 2026
·
7 of 11 tasks
·
·
3
chore(golden-al): switch the Kimi K3.1 Pro DSpark curve to the released draft Inferact/Kimi-K3.1-Pro-DSpark
#5102
·
wzhao18
opened
Nov 16, 2026
Collaborator
·
·
9
feat(config): add TokenSpeed Kimi K3.1 Pro MXFP4 MI355X AgentX with DSpark / feat(config): 新增 TokenSpeed Kimi K3.1 Pro MXFP4 MI355X AgentX(DSpark)配置
full-sweep-enabled
#5101
·
Yu-Zhewen
opened
Nov 16, 2026
·
8 of 11 tasks
·
·
1
[AMD][Qwen3.5] Run MI355X FP8 AgentX on the 20261117 image with the monokernel
#5099
·
yichiche
opened
Nov 16, 2026
Collaborator
·
·
1
[AMD][AgentX] DeepSeek-V4.1-Flash MI355X vLLM: add DEP2 (MegaMoE) concurrency 128-384, with UMBP KV offloading at 256 and 384 / [AMD][AgentX] DeepSeek-V4.1-Flash MI355X vLLM:新增 DEP2(MegaMoE)并发 128–384 点,256、384 启用 UMBP KV offloading
non-canary-full-sweep-enabled
#5098
·
Fangzhou-Ai
opened
Nov 16, 2026
Collaborator
·
·
6
[VideoGenX] Add Ascend 950DT H3 candidates for 1/2/4/8 NPUs / [VideoGenX] 新增昇腾 950DT 的 1/2/4/8 卡 H3 候选配置
#5097
·
fan2956
opened
Nov 16, 2026
·
8 of 11 tasks
·
·
1
[AMD][AgentX] DSv4.1-Flash MI355X SGLang: v0.5.23 image, fastokens, per-point max-running-requests, DP2 up to c128 / [AMD][AgentX] DSv4.1-Flash MI355X SGLang:v0.5.23 镜像、fastokens、按点设置 max-running-requests、DP2 扩展到 c128
full-sweep-fail-fast
#5096
·
xiaofei-zheng
opened
Nov 16, 2026
Collaborator
·
5 of 11 tasks
·
·
2
[GLM-5.3-Flash][H100][SGLang][AgentX] Larger KV pool and host cache for the HiCache points / [GLM-5.3-Flash][H100][SGLang][AgentX] 为 HiCache 测试点扩大 KV 缓存池与主机缓存
#5095
·
zflowai
opened
Nov 16, 2026
·
2 of 11 tasks
·
·
1
[TileRT] DeepSeek-V4.1-Flash FP4 GB300 AgentX: vLLM prefill + TileRT DEP32 decode at 4, 8 and 16 sequences per GPU / [TileRT] DeepSeek-V4.1-Flash FP4 GB300 AgentX:vLLM prefill + TileRT DEP32 decode,每卡 4 / 8 / 16 条序列
full-sweep-enabled
#5094
·
functionstackx
opened
Nov 16, 2026
Collaborator
·
·
9
[TileRT] DeepSeek-V4.1-Flash FP4 GB300 AgentX: vLLM prefill + TileRT DEP32 decode at 4, 8 and 16 sequences per GPU / [TileRT] DeepSeek-V4.1-Flash FP4 GB300 AgentX:vLLM prefill + TileRT DEP32 decode,每卡 4 / 8 / 16 条序列
#5093
·
CrimsonDump
opened
Nov 16, 2026
Contributor
·
6 of 11 tasks
·
·
4
feat(agentx): add Qwen3.5 FP4 MI355X ATOM AgentX (TP4 + TP2) on AttnFP8-V2 and nightly_202611131030, no INT4 quick all-reduce
agentx
AMD
full-sweep-enabled
#5092
·
zhuyuhua-v
opened
Nov 16, 2026
Collaborator
·
·
2
[AMD] MiniMax-M3.1-Flash MI355X vLLM: PD-disaggregated AgentX over Mooncake / [AMD] MiniMax-M3.1-Flash MI355X vLLM:基于 Mooncake 的 PD 分离 AgentX
non-canary-full-sweep-enabled
#5090
·
whx-sjtu
opened
Nov 16, 2026
Collaborator
·
5 of 11 tasks
·
·
5
fix(bench_serving): trust the environment only when a proxy or netrc entry applies / fix(bench_serving):仅在代理或 netrc 条目适用时启用 trust_env
#5088
·
oscar030406
opened
Nov 15, 2026
·
5 of 11 tasks
·
·
3
Move CI priority scoring to the scheduler / 将 CI 优先级打分移至调度器
#5085
·
adibarra
opened
Nov 15, 2026
Collaborator
·
6 of 11 tasks
·
·
8
[Fix] Link VideoGenX from the unofficial run visualizer comment / [Fix] 在非官方运行可视化评论中加入 VideoGenX 链接
#5083
·
edwingao28
opened
Nov 15, 2026
Collaborator
·
·
[wip][NVIDIA][AgentX] MiniMax-M3.1-Flash GB200 Dynamo vLLM
full-sweep-enabled
#5076
·
xinli-sw
opened
Nov 14, 2026
Collaborator
·
·
8
[wip][NVIDIA][AgentX] MiniMax-M3.1-Flash GB300
full-sweep-enabled
#5075
·
xinli-sw
opened
Nov 14, 2026
Collaborator
·
·
8
[Klaud Cold] Update GLM-5.3-Flash FP8 MI325X SGLang AgentX MTP image to v0.5.23 / [Klaud Cold] 将 GLM-5.3-Flash FP8 MI325X SGLang AgentX MTP 镜像更新至 v0.5.23
full-sweep-fail-fast
klaud-finished
#5074
·
Klaud-Cold
opened
Nov 14, 2026
Collaborator
·
·
11
fix(bench): honor the SSE end marker / fix(bench): 正确处理 SSE 结束标记
#5072
·
alaydshah
opened
Nov 13, 2026
·
·
2
[NV] Kimi-K3.1-Pro GB300 Dynamo+vLLM AgentX: new image, hybrid c448, DEP32 c960, 1P5D low-latency points / [NV] Kimi-K3.1-Pro GB300 Dynamo+vLLM AgentX:新镜像、混合 c448、DEP32 c960、1P5D 低延迟点
non-canary-full-sweep-enabled
#5069
·
mispa-ms
opened
Nov 13, 2026
Collaborator
·
6 of 11 tasks
·
·
4
[NVIDIA][AgentX] B300 Kimi-K3.1-Pro FP4 Dynamo+vLLM disaggregated configs / [NVIDIA][AgentX] B300 Kimi-K3.1-Pro FP4 Dynamo+vLLM 分离式配置
non-canary-full-sweep-enabled
#5068
·
mispa-ms
opened
Nov 13, 2026
Collaborator
·
·
6
[AgentX] MiniMax-M3.1-Flash GB300 Dynamo TRT: add disaggregated points / [AgentX] MiniMax-M3.1-Flash GB300 Dynamo TRT:新增分离式运行点
full-sweep-enabled
#5066
·
Ankur-singh
opened
Nov 13, 2026
Collaborator
·
5 of 11 tasks
·
·
6
[NVIDIA][AgentX] GB300 DSV4.1-Flash Dynamo + SGLang: megakernel agg c4, c8 and c32 / [NVIDIA][AgentX] GB300 DSV4.1-Flash Dynamo + SGLang:agg c4、c8、c32 改用 megakernel
#5065
·
weireweire
opened
Nov 13, 2026
Collaborator
·
·
3
[AMD][Qwen3.8-Flash-Next] MI325X FP8 SGLang AgentX on sglang-rocm v0.5.23-20261110 with sglang#46945 and no integer all-reduce / [AMD][Qwen3.8-Flash-Next] MI325X FP8 SGLang AgentX 升级至 sglang-rocm v0.5.23-20261110,应用 sglang#46945 并禁用整数 all-reduce
#5064
·
ZhengGong-amd
opened
Nov 13, 2026
Collaborator
·
5 of 11 tasks
·
·
4
Previous
1
2
3
4
5
6
7
Next
You can’t perform that action at this time.