-
Notifications
You must be signed in to change notification settings - Fork 206
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
CollectiveX: experimental cross-vendor collective/EP benchmark
#1896
opened Jun 23, 2026 by
Oseltamivir
Collaborator
Loading…
Add GLM-5-FP8 GB200 dynamo-sglang multinode benchmark
full-sweep-enabled
#1895
opened Jun 23, 2026 by
hshrivastava-droid
Collaborator
Loading…
Add qwen3.5-fp4-b200-trt-mtp single-node TensorRT-LLM benchmark
full-sweep-enabled
#1894
opened Jun 23, 2026 by
RohitNagraj
Collaborator
Loading…
[NV] update B300 disagg recipes (same-repo sweep copy)
full-sweep-enabled
#1891
opened Jun 23, 2026 by
jasonlizhengjian
Collaborator
Loading…
[NV] Add MiniMax M3 B300 Dynamo vLLM recipes with performance image
full-sweep-enabled
#1890
opened Jun 23, 2026 by
Oseltamivir
Collaborator
Loading…
Use MiniMax-M3 GB300 performance image and fix MNNVL workspace
full-sweep-enabled
#1888
opened Jun 22, 2026 by
Oseltamivir
Collaborator
Loading…
[AMD] dsv4 atom-disagg eval sweep — validate reduced ATOM logging
all-evals
Expand eval selection to every fixed-sequence config
evals-only
Suppress throughput and run only eval jobs; combine with all-evals to expand selection
full-sweep-enabled
#1882
opened Jun 22, 2026 by
Oseltamivir
Collaborator
Loading…
[CI] Validate aggregate benchmark results before upload
#1881
opened Jun 21, 2026 by
edwingao28
Loading…
[codex] Enforce complete eval validation and quiet ATOM logs
#1878
opened Jun 21, 2026 by
Oseltamivir
Collaborator
•
Draft
[AMD] Add MiniMax-M3-FP8 MI355X ATOM EAGLE3 only
AMD
full-sweep-enabled
#1867
opened Jun 20, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
[AMD] Add MiniMax-M3-FP4 MI355X ATOM EAGLE3 only
AMD
full-sweep-enabled
#1866
opened Jun 20, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
[AMD] Add MiniMax-M3-FP8 MI355X ATOMMESH
all-evals
Expand eval selection to every fixed-sequence config
AMD
full-sweep-enabled
#1865
opened Jun 20, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
[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
full-sweep-enabled
#1856
opened Jun 19, 2026 by
seungrokj
Collaborator
Loading…
4 tasks
[AMD] Add DSv4-FP4-MI355X ATOMMESH MTP
AMD
#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…
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
all-evals
Expand eval selection to every fixed-sequence config
AMD
full-sweep-enabled
#1818
opened Jun 18, 2026 by
billishyahao
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…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.