[CI] Migrate 6 verified jobs from gpu_1_queue to h200_18gb MIG (#42446)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kevin H. Luu
2026-05-12 11:52:01 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 67c89fe40a
commit 379f0ec369
5 changed files with 5 additions and 0 deletions
+1
View File
@@ -91,6 +91,7 @@ steps:
- label: Kernels KDA Test
timeout_in_minutes: 20
device: h200_18gb
source_file_dependencies:
- vllm/model_executor/layers/fla/ops/kda.py
- vllm/model_executor/layers/fla/ops/chunk_delta_h.py
+1
View File
@@ -114,6 +114,7 @@ steps:
- label: LM Eval TurboQuant KV Cache
key: lm-eval-turboquant-kv-cache
timeout_in_minutes: 75
device: h200_18gb
source_file_dependencies:
- vllm/model_executor/layers/quantization/turboquant/
- vllm/v1/attention/backends/turboquant_attn.py
+1
View File
@@ -212,6 +212,7 @@ steps:
depends_on: ~
optional: true
timeout_in_minutes: 20
device: h200_18gb
source_file_dependencies:
- tests/standalone_tests/python_only_compile.sh
- setup.py
+1
View File
@@ -5,6 +5,7 @@ steps:
- label: Basic Models Tests (Initialization)
key: basic-models-tests-initialization
timeout_in_minutes: 45
device: h200_18gb
torch_nightly: true
source_file_dependencies:
- vllm/
@@ -5,6 +5,7 @@ steps:
- label: Language Models Tests (Standard)
key: language-models-tests-standard
timeout_in_minutes: 25
device: h200_18gb
source_file_dependencies:
- vllm/
- tests/models/language