Skip to content

Pull requests: SemiAnalysisAI/InferenceX

New pull request New
28 Open 675 Closed
28 Open 675 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

[WIP] [AMD/ROCM] atom glm5 fp4 on mi355x AMD
#1043 opened Apr 16, 2026 by seungrokj Collaborator Loading…
3
[WIP] [AMD/ROCM] atom minimaxm2.5 fp4 on mi355x AMD
#1042 opened Apr 16, 2026 by seungrokj Collaborator Loading…
3
[WIP] [AMD/ROCM] atom qwen fp8/bf16 on mi355x AMD
#1040 opened Apr 16, 2026 by seungrokj Collaborator Loading…
3
Add full-sweep-enabled label to split sweep tiers
#1039 opened Apr 16, 2026 by n0madsky Loading…
2 of 5 tasks
1
Multiprocess Parallel Random Data Generation for Benchmark Serving.
#1038 opened Apr 16, 2026 by Duyi-Wang Loading…
Locks python dependencies for CI into a requirements.txt file and cache the dependencies
#1037 opened Apr 16, 2026 by n0madsky Loading…
[WIP] Add B300 config: qwen3.5-fp8-sglang-mtp sweep-enabled
#1035 opened Apr 16, 2026 by Ankur-singh Collaborator Loading…
3
[WIP][NV] GLM5 fp8 update sglang container NVIDIA sweep-enabled
#1033 opened Apr 15, 2026 by hshrivastava-droid Collaborator Loading…
4
[experimental] add multi-turn KV cache stress benchmark traces
#1032 opened Apr 15, 2026 by OCWC22 Loading…
4 tasks
4
[WIP][NV] update glm5-fp4-b200 sglang image NVIDIA sweep-enabled
#1031 opened Apr 15, 2026 by hshrivastava-droid Collaborator Loading…
3
[WIP][NV] update glm5 fp8 b200 sglang container NVIDIA sweep-enabled
#1030 opened Apr 14, 2026 by hshrivastava-droid Collaborator Loading…
1 task
3
Add vLLM dynamic scheduler reconfigure for single-server sweeps
#1029 opened Apr 14, 2026 by JordanNanos Collaborator Loading…
3 of 6 tasks
6
[ATOM/ROCm] atom deepseek r1 fp4 mtp3 on mi355x AMD
#1028 opened Apr 14, 2026 by seungrokj Collaborator Loading…
10
[WIP] Update Qwen3.5 FP8 B200 SGLang sweep-enabled
#1027 opened Apr 13, 2026 by Ankur-singh Collaborator Loading…
3
Add Kimi K2.5 NVFP4 GB200 disaggregated TRT-LLM benchmarks via Dynamo NVIDIA sweep-enabled
#1026 opened Apr 13, 2026 by yeswanthk-lab Collaborator Loading…
12
Upgrade GLM-5 image to v0.5.10 sweep-enabled
#1023 opened Apr 10, 2026 by chunfangamd Collaborator Loading…
@chunfangamd
11
[WIP] Update Qwen3.5 FP4 B200 SGLang sweep-enabled
#1018 opened Apr 10, 2026 by Ankur-singh Collaborator Loading…
1
[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
[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
78
[WIP][experimental] add agentic trace replay benchmark infrastructure experimental
#993 opened Apr 1, 2026 by cquil11 Collaborator • Draft
11
[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
ProTip! Exclude everything labeled bug with -label:bug.