From 155b988373cbe196e0b018ad052c1ee50d83311b Mon Sep 17 00:00:00 2001 From: "Kevin H. Luu" Date: Thu, 24 Sep 2026 18:29:44 -0700 Subject: [PATCH] [CI] Run DFlash2 NVFP4 acceptance test on B200; skip it on H200 35GB MIG (#58496) Signed-off-by: khluu Co-authored-by: Claude Opus 5.5 Co-authored-by: Misha Goin --- .buildkite/test_areas/spec_decode.yaml | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/.buildkite/test_areas/spec_decode.yaml b/.buildkite/test_areas/spec_decode.yaml index fb01306000..2baeefcc28 100644 --- a/.buildkite/test_areas/spec_decode.yaml +++ b/.buildkite/test_areas/spec_decode.yaml @@ -290,7 +290,8 @@ steps: - vllm/model_executor/models/laguna_dflash.py - tests/v1/e2e/spec_decode/ commands: - - pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ + # DFlash2 NVFP4 (27B) does not fit a 35GB MIG slice; runs on B200 below. + - pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ -k "not dflash2" mirror: amd: label: ":amd: (MI300) Spec Decode AL DFlash Nightly" @@ -316,6 +317,21 @@ steps: - tests/v1/e2e/spec_decode/ - vllm/platforms/rocm.py +- label: ":nvidia: (B200) Spec Decode AL DFlash2 Nightly" + key: spec-decode-dflash2-nightly-b200 + timeout_in_minutes: 60 + device: b200-k8s + optional: true + source_file_dependencies: + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/models/qwen3_dflash.py + - vllm/model_executor/models/qwen3_dflash2.py + - vllm/model_executor/models/qwen3_5.py + - tests/v1/e2e/spec_decode/ + commands: + - pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ -k "dflash2" + - label: ":nvidia: (H200 MIG 35GB) Spec Decode AL DSpark Nightly" key: spec-decode-dspark-nightly timeout_in_minutes: 60