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
9
(9)
Pull requests
159
(159)
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
159
(159)
Closed
4,554
(4,554)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[Klaud Cold] Update DeepSeek-V4.1-Flash FP4 MI325X vLLM AgentX DSpark image to nightly-rocm100-f8b29fab / [Klaud Cold] 将 DeepSeek-V4.1-Flash FP4 MI325X vLLM AgentX DSpark 镜像更新至 nightly-rocm100-f8b29fab
full-sweep-fail-fast
klaud-parked
#5179
·
Klaud-Cold
opened
Nov 22, 2026
Collaborator
·
·
7
[Klaud Cold] Update Qwen3.8-Flash-Next FP4 B200 SGLang AgentX MTP image to nightly-dev-cu13-20261121-a8ac8659 / [Klaud Cold] 将 Qwen3.8-Flash-Next FP4 B200 SGLang AgentX MTP 镜像更新至 nightly-dev-cu13-20261121-a8ac8659
full-sweep-fail-fast
klaud-finished
#5178
·
Klaud-Cold
opened
Nov 22, 2026
Collaborator
·
·
22
[Klaud Cold] Update Kimi-K3.1-Pro FP4 GB200 vLLM AgentX DSpark image to kimi-k31-mc-f4c9618-arm64 / [Klaud Cold] 将 Kimi-K3.1-Pro FP4 GB200 vLLM AgentX DSpark 镜像更新至 kimi-k31-mc-f4c9618-arm64
full-sweep-fail-fast
klaud-finished
#5177
·
Klaud-Cold
opened
Nov 21, 2026
Collaborator
·
·
8
[Klaud Cold] Update Qwen3.5 FP8 MI300X SGLang AgentX MTP image to v0.5.23-rocm10-mi30x-20261121 / [Klaud Cold] 将 Qwen3.5 FP8 MI300X SGLang AgentX MTP 镜像更新至 v0.5.23-rocm10-mi30x-20261121
full-sweep-fail-fast
klaud-parked
#5176
·
Klaud-Cold
opened
Nov 21, 2026
Collaborator
·
·
19
[NVIDIA][AgentX] B300 Kimi-K3.1-Pro FP4 Dynamo+vLLM disaggregated configs on kimi-k31-mc-f4c9618 / [NVIDIA][AgentX] B300 Kimi-K3.1-Pro FP4 Dynamo+vLLM 分离式配置更新到 kimi-k31-mc-f4c9618 镜像
non-canary-full-sweep-enabled
#5175
·
mispa-ms
opened
Nov 21, 2026
Collaborator
·
·
4
[Amnaro][AMD][MI300X][DS V4.1 Flash] vLLM TP4: mono decode on the first N layers (--monokernel-layers) / [Amnaro][AMD][MI300X][DS V4.1 Flash] vLLM TP4:仅在前 N 层启用 mono decode(--monokernel-layers)
#5174
·
Qam2ng
opened
Nov 21, 2026
·
4 of 11 tasks
·
·
1
[Klaud Cold] Update DeepSeek-V4.1-Flash FP4 MI300X vLLM AgentX DSpark image to nightly-rocm100-f8b29fab / [Klaud Cold] 将 DeepSeek-V4.1-Flash FP4 MI300X vLLM AgentX DSpark 镜像更新至 nightly-rocm100-f8b29fab
full-sweep-fail-fast
klaud-finished
#5172
·
Klaud-Cold
opened
Nov 21, 2026
Collaborator
·
·
11
[MI325] DSv41 PD disagg
#5169
·
simondanielsson
opened
Nov 21, 2026
Contributor
·
·
2
[AMD][AgentX] Re-sweep GLM-5.3 FP8 with Triton DSA / [AMD][AgentX] 使用 Triton DSA 重跑 GLM-5.3 FP8 sweep
agentx
AMD
full-sweep-fail-fast
#5168
·
jiejingzhangamd
opened
Nov 21, 2026
Collaborator
·
6 of 11 tasks
·
·
5
[Klaud Cold] Update GLM-5.3-Flash FP8 B200 SGLang AgentX MTP image to v0.5.23-cu130 / [Klaud Cold] 将 GLM-5.3-Flash FP8 B200 SGLang AgentX MTP 镜像更新至 v0.5.23-cu130
full-sweep-fail-fast
klaud-finished
#5165
·
Klaud-Cold
opened
Nov 21, 2026
Collaborator
·
·
10
AGENTS.md: subset sweeps require the same image and append-only
#5164
·
functionstackx
opened
Nov 20, 2026
Collaborator
·
·
[NV] Qwen3.8-Flash-Next FP4 B300 SGLang AgentX: image bump, sglang#51074 env renames, c80 retune / [NV] Qwen3.8-Flash-Next FP4 B300 SGLang AgentX:镜像升级、sglang#51074 环境变量重命名、c80 调优
#5163
·
vincentzed
opened
Nov 20, 2026
·
·
1
[AMD][MiniMax-M3.1-Flash] MI325X MXFP4 vLLM AgentX with DSpark on the vllm-openai-rocm 153dc0464 nightly / [AMD][MiniMax-M3.1-Flash] 新增 MI325X MXFP4 vLLM AgentX(DSpark),使用 vllm-openai-rocm 153dc0464 nightly
#5161
·
ZhengGong-amd
opened
Nov 20, 2026
Collaborator
·
5 of 11 tasks
·
·
1
[AMD][AgentX] DeepSeek-V4.1-Flash MI355X vLLM: append TP4 concurrency 4-48 with running-request caps / [AMD][AgentX] DeepSeek-V4.1-Flash MI355X vLLM:追加 TP4 并发 4–48 点(限制同时运行的请求数)
full-sweep-fail-fast
#5158
·
fanxingran
opened
Nov 20, 2026
Collaborator
·
6 of 11 tasks
·
·
5
feat(agentx): MiniMax-M3.1-Flash FP4 MI355X ATOM AgentX on nightly_202611200431, NVFP4 KV, served as shipped / feat(agentx):MiniMax-M3.1-Flash FP4 MI355X ATOM AgentX,基于 nightly_202611200431,NVFP4 KV,按原样服务
agentx
AMD
full-sweep-enabled
#5157
·
zhuyuhua-v
opened
Nov 20, 2026
Collaborator
·
·
7
ci: alert when a whole runner pool is offline; document reboot-safe runners / ci:整个 runner 池离线时告警;补充重启后可自动恢复的 runner 配置
#5156
·
chunfangamd
opened
Nov 20, 2026
Collaborator
·
6 of 11 tasks
·
·
musespark mi355x: append TP4/EP4 concurrency 58 / musespark mi355x:追加 TP4/EP4 并发 58
#5155
·
dorado269
opened
Nov 20, 2026
·
4 of 11 tasks
·
·
1
[NV] MiniMax-M3.1-Flash on GB300: FP4 Dynamo vLLM — DSpark agg and disagg AgentX points on cu135 image / [NV] MiniMax-M3.1-Flash 在 GB300 上:FP4 Dynamo vLLM — 基于 cu135 镜像的 DSpark 聚合与分离式 AgentX 测试点
non-canary-full-sweep-enabled
#5153
·
RohitNagraj
opened
Nov 20, 2026
Collaborator
·
3 of 11 tasks
·
·
2
[AMD][MI325X] DSv4.1 Flash vLLM: dense decode CUDA graphs at TP4 c16 on the f5d93296 nightly / [AMD][MI325X] DSv4.1 Flash vLLM:在 f5d93296 nightly 上为 TP4 c16 启用密集 decode CUDA graph
full-sweep-fail-fast
#5152
·
ZhengGong-amd
opened
Nov 20, 2026
Collaborator
·
5 of 11 tasks
·
·
5
Run GLM-5.3-Flash MI300X/MI325X block-FP8 linears on aiter's CK GEMM / GLM-5.3-Flash MI300X/MI325X 的 block-FP8 线性层改用 aiter CK GEMM
full-sweep-fail-fast
#5150
·
fengshaoyi-amd
opened
Nov 20, 2026
Collaborator
·
6 of 11 tasks
·
·
4
[K3.1-Pro] Add GB300 FP4 disaggregated llmd-vllm AgentX configs / [K3.1-Pro] 新增 GB300 FP4 分离式 llmd-vllm AgentX 配置
non-canary-full-sweep-enabled
#5149
·
cquil11
opened
Nov 19, 2026
Collaborator
·
·
6
[NV] GLM-5.3 on GB300: NVFP4 Dynamo TensorRT-LLM — Add disaggregated AgentX / [NV] GLM-5.3 在 GB300 上:NVFP4 Dynamo TensorRT-LLM — 新增 AgentX 分离式配置
non-canary-full-sweep-enabled
#5148
·
RohitNagraj
opened
Nov 19, 2026
Collaborator
·
5 of 11 tasks
·
·
3
perf(qwen3.5): GB300 TRT AgentX on TRT-LLM 1.4.0rc4 with remote KV cache / perf(qwen3.5):GB300 TRT AgentX 改用 TRT-LLM 1.4.0rc4 与远程 KV 缓存
non-canary-full-sweep-enabled
#5147
·
richardhuo-nv
opened
Nov 19, 2026
Collaborator
·
6 of 11 tasks
·
·
5
chore: bump srt-slurm to v2.73.0 / chore:将 srt-slurm 升级到 v2.73.0
#5145
·
seungrokj
opened
Nov 19, 2026
Collaborator
·
·
3
[NVIDIA][AgentX] GB300 Muse Spark Open Dynamo+SGLang: retune on the 20261119 nightly / [NVIDIA][AgentX] GB300 Muse Spark Open Dynamo+SGLang:基于 20261119 nightly 重新调优
full-sweep-fail-fast
#5143
·
shyeh25
opened
Nov 19, 2026
Collaborator
·
4 of 11 tasks
·
·
5
Previous
1
2
3
4
5
6
7
Next
You can’t perform that action at this time.