-
Notifications
You must be signed in to change notification settings - Fork 204
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[AMD] Add MiniMax-M3-FP8 MI355X ATOM non-EAGLE3 & EAGLE3
AMD
full-sweep-enabled
#1867
opened Jun 20, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
[AMD] Add MiniMax-M3-FP4 MI355X ATOM EAGLE3
AMD
#1866
opened Jun 20, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
[AMD] Add MiniMax-M3-FP8 MI355X ATOMMESH
AMD
full-sweep-enabled
#1865
opened Jun 20, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
[NV] Add MiniMax M3 B300 Dynamo vLLM recipes
full-sweep-enabled
#1863
opened Jun 19, 2026 by
Oseltamivir
Collaborator
Loading…
[NV] Kimi-K2.5 NVFP4 GB200 dynamo-vllm disagg benchmark refresh
full-sweep-fail-fast
#1862
opened Jun 19, 2026 by
xinli-sw
Collaborator
Loading…
[Klaud Cold] MI300X MiniMax-M3 nightly image and FP8 KV cache
full-sweep-fail-fast
#1858
opened Jun 19, 2026 by
cquil11
Collaborator
Loading…
[AMD] Add MiniMax-M3-FP4 MI355X ATOMMESH
all-evals
Expand eval selection to every fixed-sequence config
AMD
evals-only
Suppress throughput and run only eval jobs; combine with all-evals to expand selection
full-sweep-enabled
#1856
opened Jun 19, 2026 by
seungrokj
Collaborator
Loading…
4 tasks
[AMD] Add DSv4-FP4-MI355X ATOMMESH MTP
AMD
full-sweep-enabled
#1855
opened Jun 19, 2026 by
seungrokj
Collaborator
Loading…
2 tasks
[AMD] Optimize MiniMax M3 sparse index scoring on MI300X
sweep-enabled
#1840
opened Jun 18, 2026 by
Oseltamivir
Collaborator
Loading…
[Klaud Cold] MI325X MiniMax-M3 EAGLE3 nightly image and FP8 KV cache
full-sweep-fail-fast
#1838
opened Jun 18, 2026 by
cquil11
Collaborator
Loading…
[codex] Update MiniMax M3 B300 EAGLE3 FlashInfer image
full-sweep-fail-fast
#1835
opened Jun 18, 2026 by
cquil11
Collaborator
Loading…
[codex] Update MiniMax M3 B300 FlashInfer image
full-sweep-fail-fast
#1834
opened Jun 18, 2026 by
cquil11
Collaborator
Loading…
[codex] Update MiniMax M3 B200 FlashInfer image
full-sweep-fail-fast
#1833
opened Jun 18, 2026 by
cquil11
Collaborator
Loading…
[codex] Update MiniMax M3 B200 EAGLE3 FlashInfer image
full-sweep-fail-fast
#1832
opened Jun 18, 2026 by
cquil11
Collaborator
Loading…
fix(ci): bound multinode pre-run Slurm cleanup drain loop (unblocks NVIDIA sweeps)
#1820
opened Jun 18, 2026 by
arygupt
Collaborator
Loading…
[AMD] add dsv4 sglang disagg
AMD
full-sweep-enabled
#1818
opened Jun 18, 2026 by
billishyahao
Collaborator
Loading…
Add Qwen3.5-FP8 GB200 SGLang disaggregated benchmark
full-sweep-enabled
#1810
opened Jun 16, 2026 by
RohitNagraj
Collaborator
Loading…
[AMD] [MI300X] minimaxm3-fp8-mi300x-vllm: enable AITER kernels for MXFP8 on MI300X
full-sweep-enabled
#1808
opened Jun 16, 2026 by
JohnQinAMD
Collaborator
Loading…
Fix for https://github.com/sgl-project/sglang/issues/22072
#1806
opened Jun 16, 2026 by
davzhuAMD
Loading…
[NV]Add GLM-5 NVFP4 GB200 disagg non-mtp TRT-LLM benchmarks via Dynamo
full-sweep-enabled
#1803
opened Jun 16, 2026 by
xinli-sw
Collaborator
Loading…
[NV]Add GLM-5 NVFP4 GB200 disagg-mtp TRT-LLM benchmarks via Dynamo
full-sweep-enabled
#1800
opened Jun 16, 2026 by
xinli-sw
Collaborator
Loading…
[NV]Add GLM-5 NVFP4 GB300 disagg-mtp TRT-LLM benchmarks via Dynamo
full-sweep-enabled
#1799
opened Jun 16, 2026 by
xinli-sw
Collaborator
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-05-20.