[CI] Route part of B200 jobs to b200-k8s (#41453)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Kevin H. Luu
2026-05-05 19:00:30 -07:00
committed by GitHub
co-authored by OpenAI Codex
parent 4a8ae26e53
commit f653761252
10 changed files with 15 additions and 15 deletions
+1 -1
View File
@@ -17,7 +17,7 @@ steps:
- label: V1 attention (B200)
key: v1-attention-b200
timeout_in_minutes: 30
device: b200
device: b200-k8s
source_file_dependencies:
- vllm/config/attention.py
- vllm/model_executor/layers/attention
+1 -1
View File
@@ -14,7 +14,7 @@ steps:
- label: Attention Benchmarks Smoke Test (B200)
key: attention-benchmarks-smoke-test-b200
device: b200
device: b200-k8s
num_gpus: 2
optional: true
working_dir: "/vllm-workspace/"
+4 -4
View File
@@ -43,7 +43,7 @@ steps:
key: asynctp-correctness-tests-b200
timeout_in_minutes: 50
working_dir: "/vllm-workspace/"
device: b200
device: b200-k8s
optional: true
num_devices: 2
commands:
@@ -68,7 +68,7 @@ steps:
key: fusion-and-compile-unit-tests-2xb200
timeout_in_minutes: 20
working_dir: "/vllm-workspace/"
device: b200
device: b200-k8s
source_file_dependencies:
- csrc/quantization/fp4/
- vllm/model_executor/layers/quantization/
@@ -137,7 +137,7 @@ steps:
key: fusion-e2e-config-sweep-b200
timeout_in_minutes: 30
working_dir: "/vllm-workspace/"
device: b200
device: b200-k8s
num_devices: 1
optional: true
commands:
@@ -209,7 +209,7 @@ steps:
key: fusion-e2e-tp2-b200
timeout_in_minutes: 20
working_dir: "/vllm-workspace/"
device: b200
device: b200-k8s
num_devices: 2
source_file_dependencies:
- csrc/quantization/
+1 -1
View File
@@ -212,7 +212,7 @@ steps:
- label: Distributed Tests (2 GPUs)(B200)
key: distributed-tests-2-gpus-b200
device: b200
device: b200-k8s
optional: true
working_dir: "/vllm-workspace/"
num_devices: 2
+1 -1
View File
@@ -25,7 +25,7 @@ steps:
- label: Qwen3-30B-A3B-FP8-block Accuracy (B200)
key: qwen3-30b-a3b-fp8-block-accuracy-b200
timeout_in_minutes: 60
device: b200
device: b200-k8s
optional: true
num_devices: 2
working_dir: "/vllm-workspace"
+2 -2
View File
@@ -125,7 +125,7 @@ steps:
key: kernels-b200
timeout_in_minutes: 30
working_dir: "/vllm-workspace/"
device: b200
device: b200-k8s
# optional: true
source_file_dependencies:
- csrc/quantization/fp4/
@@ -212,7 +212,7 @@ steps:
- label: Kernels Fp4 MoE Test (B200)
key: kernels-fp4-moe-test-b200
timeout_in_minutes: 60
device: b200
device: b200-k8s
num_devices: 1
optional: true
commands:
+2 -2
View File
@@ -51,7 +51,7 @@ steps:
- label: LM Eval Qwen3.5 Models (B200)
key: lm-eval-qwen3-5-models-b200
timeout_in_minutes: 120
device: b200
device: b200-k8s
optional: true
num_devices: 2
source_file_dependencies:
@@ -84,7 +84,7 @@ steps:
- label: MoE Refactor Integration Test (B200 - TEMPORARY)
key: moe-refactor-integration-test-b200-temporary
device: b200
device: b200-k8s
optional: true
num_devices: 2
commands:
+1 -1
View File
@@ -224,7 +224,7 @@ steps:
- label: Batch Invariance (B200)
key: batch-invariance-b200
timeout_in_minutes: 30
device: b200
device: b200-k8s
source_file_dependencies:
- vllm/v1/attention
- vllm/model_executor/layers
+1 -1
View File
@@ -25,7 +25,7 @@ steps:
key: quantized-moe-test-b200
timeout_in_minutes: 60
working_dir: "/vllm-workspace/"
device: b200
device: b200-k8s
source_file_dependencies:
- tests/quantization/test_blackwell_moe.py
- vllm/model_executor/models/deepseek_v2.py
+1 -1
View File
@@ -75,7 +75,7 @@ steps:
- label: Spec Decode Draft Model Nightly B200
key: spec-decode-draft-model-nightly-b200
timeout_in_minutes: 30
device: b200
device: b200-k8s
optional: true
source_file_dependencies:
- vllm/v1/spec_decode/