[CI] Run DFlash2 NVFP4 acceptance test on B200; skip it on H200 35GB MIG (#58496)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
This commit is contained in:
Kevin H. Luu
2026-09-24 19:29:44 -06:00
committed by GitHub
co-authored by Claude Opus 5.5 Misha Goin
parent 34ee85d5ca
commit 155b988373
+17 -1
View File
@@ -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