[CI] Add headroom and selection coverage for H200 fast lanes (#56775)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com> Co-authored-by: Sherlock <sherlock@raft.ai>
This commit is contained in:
@@ -4,7 +4,7 @@ depends_on:
|
||||
steps:
|
||||
- label: ":nvidia: (H200 MIG 18GB) Benchmarks CLI"
|
||||
key: benchmarks-cli-test
|
||||
timeout_in_minutes: 45
|
||||
timeout_in_minutes: 55
|
||||
device: h200_18gb
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
|
||||
@@ -33,14 +33,19 @@ steps:
|
||||
- label: ":nvidia: (H200 MIG 18GB) CUDAGraph"
|
||||
device: h200_18gb
|
||||
key: cudagraph
|
||||
timeout_in_minutes: 30
|
||||
timeout_in_minutes: 45
|
||||
source_file_dependencies:
|
||||
- tests/v1/cudagraph
|
||||
- vllm/v1/cudagraph_dispatcher.py
|
||||
- vllm/config/compilation.py
|
||||
- vllm/config/vllm.py
|
||||
- vllm/compilation
|
||||
- vllm/v1/worker/gpu/cudagraph_utils.py
|
||||
- vllm/v1/worker/gpu/dp_utils.py
|
||||
- vllm/v1/worker/encoder_cudagraph.py
|
||||
- vllm/v1/worker/encoder_cudagraph_defs.py
|
||||
- vllm/v1/worker/gpu/model_runner.py
|
||||
- vllm/v1/worker/gpu/ubatch_utils.py
|
||||
commands:
|
||||
- pytest -v -s v1/cudagraph/test_cudagraph_dispatch.py
|
||||
- pytest -v -s v1/cudagraph/test_cudagraph_mode.py
|
||||
|
||||
@@ -4,7 +4,7 @@ depends_on:
|
||||
steps:
|
||||
- label: ":nvidia: (H200 MIG 18GB) V1 Sample"
|
||||
key: v1-sample
|
||||
timeout_in_minutes: 35
|
||||
timeout_in_minutes: 45
|
||||
device: h200_18gb
|
||||
source_file_dependencies: &v1-sample-logits-deps
|
||||
- vllm/config/
|
||||
@@ -38,7 +38,7 @@ steps:
|
||||
|
||||
- label: ":nvidia: (H200 MIG 18GB) V1 Logits + Oracle"
|
||||
key: v1-logits-oracle
|
||||
timeout_in_minutes: 35
|
||||
timeout_in_minutes: 45
|
||||
device: h200_18gb
|
||||
source_file_dependencies: *v1-sample-logits-deps
|
||||
commands:
|
||||
|
||||
Reference in New Issue
Block a user