Skip to content

Pull requests: SemiAnalysisAI/InferenceX

New pull request New
21 Open 593 Closed
21 Open 593 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

Optimize Kimi-K2.5-MXFP4 on MI355X: Enable AITER, Expert Parallel, and update to vLLM v0.18.0
#936 opened Mar 24, 2026 by ChuanLi1101 Loading…
1 task done
9
[WIP] Enable VLLM_USE_FLASHINFER_MOE_INT4=1 for Kimi K2.5 INT4 B200 NVIDIA sweep-enabled
#935 opened Mar 23, 2026 by ankursingh-nv Loading…
4
fix: add --exclusive to MI300X SLURM salloc for accurate benchmarks
#930 opened Mar 23, 2026 by cquil11 Loading…
1 task
1
[AMD/ROCm] Do not merge - kimik2.5 fp4 mi355x perf regression test
#928 opened Mar 23, 2026 by seungrokj • Draft
5
Disable prefix cache for kimi vllm configs sweep-enabled
#926 opened Mar 23, 2026 by Oseltamivir Loading…
1
[WIP] Add Qwen3.5 h200 MTP NVIDIA sweep-enabled
#921 opened Mar 20, 2026 by hshrivastava-droid Loading…
9
test
#917 opened Mar 18, 2026 by functionstackx Loading…
4
Separate eval-only workflow and change to 8k1k sweep-enabled
#911 opened Mar 15, 2026 by Oseltamivir Loading…
@Oseltamivir
49
[AMD/ROCm] kimik2.5 int4 mi355x update
#909 opened Mar 13, 2026 by seungrokj • Draft
2
fix: multi-turn benchmark hangs after all clients finish
#908 opened Mar 13, 2026 by lishicheng1996-nv Loading…
3 of 4 tasks
3
[NVIDIA] Update NVIDIA GPT-OSS vLLM image from v0.15.1 to v0.16.0 sweep-enabled
#904 opened Mar 10, 2026 by cquil11 Loading…
1
4
[WIP] add perf comparison on non-main brances with run-sweep workflow sweep-enabled
#880 opened Mar 6, 2026 by cquil11 Loading…
6
Add Kimi-K2.5 INT4 vLLM v0.16.0 benchmark for MI300X AMD sweep-enabled
#860 opened Mar 3, 2026 by functionstackx Loading…
1
2
chore: upgrade h200 gptoss to latest trtllm
#854 opened Mar 2, 2026 by cquil11 Loading…
@jgangani
3
Add MiniMax M2.5 MXFP4 benchmark for MI355x vLLM v0.17.1 (TP=2,4) AMD sweep-enabled
#827 opened Mar 1, 2026 by functionstackx Loading…
1
4
[WIP][experimental] multi turn chat benchmark
#821 opened Feb 27, 2026 by cquil11 • Draft
[NV] Qwen3.5 B200 SGLang FP4 configs NVIDIA sweep-enabled
#820 opened Feb 27, 2026 by kedarpotdar-nv Loading…
@kedarpotdar-nv
11
[NVIDIA] Update NVIDIA single-node DSR1 SGLang images from v0.5.6-v0.5.8 to v0.5.9 image update NVIDIA sweep-enabled
#814 opened Feb 26, 2026 by cquil11 Loading…
1
@ankursingh-nv
Performance Improvements for MI300X with GEMM and FP8 Enhancements
#811 opened Feb 26, 2026 by chunfangamd Loading…
4
[WIP] [NV] Updates SGLang DSR1-FP4 GB300 1k8k configurations (STP only) NVIDIA
#637 opened Feb 5, 2026 by yunzhoul-nv Loading…
1
[WIP] [NV] Updates SGLang DSR1-FP4 GB200 1k8k (STP only) NVIDIA
#634 opened Feb 5, 2026 by yunzhoul-nv • Draft
1
ProTip! Updated in the last three days: updated:>2026-03-21.