Skip to content

Pull requests: SemiAnalysisAI/InferenceX

New pull request New
15 Open 632 Closed
15 Open 632 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

[code not in mergable state yet] Add MI325X DeepSeek-R1 FP8 disaggregated inference with Broadcom Thor 2 IBGDA
#985 opened Mar 31, 2026 by JordanNanos • Draft
2 of 8 tasks
1
14
[AMD/ROCM] ATOM DS R1 FP8 MTP 3 tokens support
#984 opened Mar 31, 2026 by seungrokj Loading…
4
[AMD] improve dsr1 fp4 disagg perf on mi355x
#983 opened Mar 31, 2026 by billishyahao Loading…
3
[Do not merge][AMD]Update cli args for qwen3.5
#980 opened Mar 30, 2026 by zhentaocc Loading…
10
[AMD/ROCM] ATOM support for new models: Kimi-K2.5 FP4, GLM-5 FP8, and MiniMax-M2.5 AMD
#963 opened Mar 27, 2026 by seungrokj Loading…
25
[DNM - vllm 0.18 is bugged, need to wait till 0.19] Add MiniMax M2.5 NVFP4 benchmark for B200 vLLM (TP4, TP2) vllm/sglang release broken -need to wait
#952 opened Mar 27, 2026 by functionstackx • Draft
1
5
[Draft, no merge] MVP for vLLM Disagg
#948 opened Mar 26, 2026 by chunfangamd Loading…
5
[WIP] B200 Minimax FP8 vllm upgrade NVIDIA sweep-enabled
#947 opened Mar 26, 2026 by kedarpotdar-nv Loading…
9
Add Qwen3.5 h200 MTP NVIDIA sweep-enabled
#921 opened Mar 20, 2026 by hshrivastava-droid Loading…
14
fix: multi-turn benchmark hangs after all clients finish
#908 opened Mar 13, 2026 by lishicheng1996-nv Loading…
3 of 4 tasks
3
chore: upgrade h200 gptoss to latest trtllm
#854 opened Mar 2, 2026 by cquil11 Loading…
@jgangani
8
[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 Loading…
1
5
[WIP][experimental] multi turn chat benchmark
#821 opened Feb 27, 2026 by cquil11 • Draft
3
[NV - WIP] Qwen3.5 B200 SGLang FP4 configs NVIDIA sweep-enabled
#820 opened Feb 27, 2026 by kedarpotdar-nv Loading…
@kedarpotdar-nv
15
Performance Improvements for MI300X with GEMM and FP8 Enhancements
#811 opened Feb 26, 2026 by chunfangamd Loading…
4
ProTip! Mix and match filters to narrow down what you’re looking for.