Skip to content

Pull requests: SemiAnalysisAI/InferenceX

New pull request New
54 Open 881 Closed
54 Open 881 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

[AMD] Add DSv4 FP4 MI355X vLLM benchmark sweep-enabled
#1282 opened May 5, 2026 by Oseltamivir Collaborator Loading…
5 tasks
6
[WIP][NV] Qwen3.5 fp4 b200 trt full-sweep-enabled NVIDIA
#1280 opened May 4, 2026 by hshrivastava-droid Collaborator Loading…
10
[BLOCKED BY TRT PR] Add DSv4 B200 TRT full-sweep-enabled
#1277 opened May 4, 2026 by Oseltamivir Collaborator Loading…
6
Tune MiniMax MI355X vLLM scheduling thresholds
#1276 opened May 4, 2026 by jiacao-amd Collaborator Loading…
6
Bump actions/setup-python from 5 to 6 in the github-actions group dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#1274 opened May 4, 2026 by dependabot Bot Loading…
2
[codex] Use PR41015 fix setup for GB200 MTP2 high throughput full-sweep-enabled
#1273 opened May 4, 2026 by alec-flowers Collaborator Loading…
2
[WIP] Updated DSv4 vllm B300 MTP full-sweep-enabled
#1271 opened May 4, 2026 by wzhao18 Collaborator Loading…
4
[DNM - test PR, waiting for nvidia/tensorrtllm to accept the fusedmhc patch] Update DSV4 TRT fused MHC image full-sweep-enabled
#1270 opened May 3, 2026 by Oseltamivir Collaborator Loading…
5
fix(dsv4): gate h200 reasoning parser flag
#1263 opened May 2, 2026 by OCWC22 Loading…
2
feat: add vLLM + LMCache CPU offloading for MiniMax-M2.5 agentic benchmark on AMD GPUs
#1262 opened May 2, 2026 by andyluo7 Collaborator • Draft
6 of 7 tasks
15
Clean up DSv4 ATOM AITER PR2998 overlay full-sweep-enabled
#1260 opened May 2, 2026 by Oseltamivir Collaborator Loading…
1 task
25
[testing][experimental] agentx v0.2 testing
#1258 opened May 1, 2026 by cquil11 Collaborator • Draft
1
[NV] qwen3.5 fp4 b200 sglang mtp full-sweep-enabled NVIDIA
#1257 opened May 1, 2026 by hshrivastava-droid Collaborator Loading…
17
[AMD][ROCM] Add MI355X Config: glm5-fp4-mi355x-sglang-mtp
#1254 opened May 1, 2026 by ChangLiu0709 Collaborator • Draft
4 of 5 tasks
1
[AMD][ROCM] Fix benchmark_serving Rust Tokenizer Crash via Direct transformers AutoTokenizer
#1253 opened May 1, 2026 by ChangLiu0709 Collaborator • Draft
3 of 4 tasks
2
Add SGLANG_OPT_USE_MULTI_STREAM_OVERLAP=1 to SGLang DSv4 launch configs full-sweep-enabled
#1246 opened May 1, 2026 by yhyang201 Collaborator Loading…
2 tasks
2
[AMD] Update MI355x Deepseek-R1 FP4 SGLang Image to v0.5.10
#1237 opened Apr 30, 2026 by ppalanga Collaborator Loading…
5
[AMD] improve dsr1 fp4 disagg perf on mi355x AMD full-sweep-enabled
#1236 opened Apr 30, 2026 by billishyahao Collaborator Loading…
31
Haichen/kimi k2.5 int4 mtp v0.19.1
#1235 opened Apr 30, 2026 by haic0 Collaborator • Draft
1
Larryli2/minimax m2.5 fp8 eagle3
#1234 opened Apr 30, 2026 by larryli2-amd Collaborator • Draft
@larryli2-amd
5
GB300 SGLang disagg recipe
#1227 opened Apr 29, 2026 by yhyang201 Collaborator Loading…
3
GB300 SGLang disagg
#1226 opened Apr 29, 2026 by yhyang201 Collaborator Loading…
3
sglang-update
#1225 opened Apr 29, 2026 by yhyang201 Collaborator Loading…
12
Haichen/kimi k2.5 int4 mtp vllm v0.20.0/modelrunnerV2
#1219 opened Apr 29, 2026 by haic0 Collaborator • Draft
1
feat(runners): add GMI Cloud launchers (H100/H200/B200/B300/GB200)
#1216 opened Apr 28, 2026 by OCWC22 • Draft
4 tasks
ProTip! no:milestone will show everything without a milestone.