Skip to content

Pull requests: SemiAnalysisAI/InferenceX

New pull request New
21 Open 662 Closed
21 Open 662 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Upgrade GLM-5 image to v0.5.10
#1023 opened Apr 10, 2026 by chunfangamd Collaborator Loading…
@chunfangamd
7
[AMD/ROCM] qwen3.5 fp4 on mi355x, search space TP2/TP4
#1022 opened Apr 10, 2026 by seungrokj Collaborator Loading…
3
Fix config/script consistency: remove bogus ep, add missing env var checks
#1019 opened Apr 10, 2026 by Ankur-singh Collaborator Loading…
2
[WIP] Update Qwen3.5 FP4 B200 SGLang sweep-enabled
#1018 opened Apr 10, 2026 by Ankur-singh Collaborator Loading…
1
[WIP][NV] Update: sglang v2 Qwen3.5 h200 MTP NVIDIA sweep-enabled
#1017 opened Apr 8, 2026 by hshrivastava-droid Collaborator Loading…
4
[AMD] Upgrade DeepSeek-R1 MI35x docker to the latest SGLang version 0.5.10 AMD
#1013 opened Apr 8, 2026 by aarnetalman Collaborator • Draft
6
[NVIDIA] [WIP] Bump GLM-5 FP8 B200 SGLang concurrency to 256 NVIDIA sweep-enabled
#1012 opened Apr 8, 2026 by Ankur-singh Collaborator Loading…
5
[experimental] Add multinode profiling workflow experimental github_actions Pull requests that update GitHub Actions code
#1007 opened Apr 6, 2026 by hbarclay Collaborator Loading…
@hbarclay
7
Multinode evals
#1000 opened Apr 3, 2026 by Oseltamivir Collaborator Loading…
3
[AMD] feat: MiniMax M2.5 PD Disagg (1P2D) + PIECEWISE cudagraph optimization (+20% throughput) AMD vllm/sglang release broken -need to wait
#999 opened Apr 2, 2026 by ChuanLi1101 Contributor • Draft
6 tasks done
3
feat: MI300X disaggregated inference with Broadcom IBGDA (#982) sweep-enabled
#998 opened Apr 2, 2026 by JordanNanos Collaborator Loading…
1
50
[AMD/ROCm] qwen3.5 fp8 mi355x SGL performance update AMD
#995 opened Apr 2, 2026 by seungrokj Collaborator • Draft
3
[WIP][experimental] add agentic trace replay benchmark infrastructure experimental
#993 opened Apr 1, 2026 by cquil11 Collaborator • Draft
4
[AMD][MI30X]Update Qwen3.5 perf AMD
#986 opened Apr 1, 2026 by zhentaocc Collaborator Loading…
@zhentaocc
17
[AMD] [code not in mergable state yet][blocker waiting for more nodes to speed up dev iteration speed] mi325 sglang disagg AMD
#985 opened Mar 31, 2026 by JordanNanos Collaborator • Draft
2 of 8 tasks
1
33
[AMD] improve dsr1 fp4 disagg perf on mi355x AMD
#983 opened Mar 31, 2026 by billishyahao Collaborator Loading…
3
[AMD][MI35X]Update qwen3.5 perf AMD
#980 opened Mar 30, 2026 by zhentaocc Collaborator Loading…
@zhentaocc
10
[AMD] [Draft, no merge] MVP for vLLM Disagg AMD
#948 opened Mar 26, 2026 by chunfangamd Collaborator Loading…
7
[NVIDIA] chore: upgrade h200 gptoss to latest trtllm NVIDIA
#854 opened Mar 2, 2026 by cquil11 Collaborator Loading…
@jgangani
8
[AMD] [DNM, still merge in 0.18 as trust_remote_code=True is not passed to quark] Add MiniMax M2.5 MXFP4 benchmark for MI355x vLLM v0.17.1 (TP=2,4) AMD vllm/sglang release broken -need to wait
#827 opened Mar 1, 2026 by functionstackx Contributor Loading…
1
10
[AMD] Performance Improvements for MI300X with GEMM and FP8 Enhancements AMD sweep-enabled
#811 opened Feb 26, 2026 by chunfangamd Collaborator Loading…
12
ProTip! Filter pull requests by the default branch with base:main.