[ci] Limit num gpus if specified for A100 (#5694)

Signed-off-by: kevin <kevin@anyscale.com>
This commit is contained in:
Kevin H. Luu 2024-06-19 16:30:03 -07:00 committed by GitHub
parent 4a30d7e3cc
commit 949e49a685
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 1 deletions

View File

@ -184,6 +184,7 @@ steps:
- label: Distributed Tests (A100) - label: Distributed Tests (A100)
gpu: a100 gpu: a100
num_gpus: 4
commands: commands:
# NOTE: don't test llama model here, it seems hf implementation is buggy # NOTE: don't test llama model here, it seems hf implementation is buggy
# see https://github.com/vllm-project/vllm/pull/5689 for details # see https://github.com/vllm-project/vllm/pull/5689 for details

View File

@ -75,7 +75,7 @@ steps:
- "'cd {{ (step.working_dir or default_working_dir) | safe }} && {{ step.command or (step.commands | join(' && ')) | safe }}'" - "'cd {{ (step.working_dir or default_working_dir) | safe }} && {{ step.command or (step.commands | join(' && ')) | safe }}'"
resources: resources:
limits: limits:
nvidia.com/gpu: 8 nvidia.com/gpu: {{ step.num_gpus or 1 }}
volumeMounts: volumeMounts:
- name: devshm - name: devshm
mountPath: /dev/shm mountPath: /dev/shm