We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 86ba33f commit fd35ba3Copy full SHA for fd35ba3
1 file changed
perf-changelog.yaml
@@ -3431,13 +3431,6 @@
3431
- "Same 1k/1k and 8k/1k search space as gb300, plus a new tp8-1p1d at low concurrencies for both ISLs"
3432
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1652
3433
3434
-- config-keys:
3435
- - minimaxm2.5-fp4-gb300-dynamo-vllm
3436
- description:
3437
- - "Add MiniMax-M2.5 NVFP4 GB300 disaggregated multinode vLLM benchmarks via Dynamo"
3438
- - "Add 1k1k/8k1k minimax recipe set under benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m2.5/"
3439
- pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1641
3440
-
3441
- config-keys:
3442
- minimaxm2.5-fp8-gb200-dynamo-vllm
3443
description:
0 commit comments