xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 07:24:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Shard tests for LoRA and Kernels to speed up (#3445)

Browse Source
This commit is contained in:
Simon Mo 2024-03-17 14:56:30 -07:00 committed by GitHub
parent abfc4f3387
commit 93348d9458
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
.buildkite/test-pipeline.yaml
View File

@ -33,9 +33,9 @@ steps:
- label: Entrypoints Test
command: pytest -v -s entrypoints
- label: Kernels Test
command: pytest -v -s kernels
soft_fail: true
- label: Kernels Test %N
command: pytest -v -s kernels --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
parallelism: 4
- label: Models Test
commands:
@ -55,8 +55,9 @@ steps:
- label: Speculative decoding tests
command: pytest -v -s spec_decode
- label: LoRA Test
command: pytest -v -s lora --forked
- label: LoRA Test %N
command: pytest -v -s lora --forked --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
parallelism: 4
- label: Metrics Test
command: pytest -v -s metrics

3
.buildkite/test-template.j2
View File

@ -20,6 +20,9 @@ steps:
agents:
queue: kubernetes
soft_fail: {{ step.soft_fail or false }}
{% if step.parallelism %}
parallelism: {{ step.parallelism }}
{% endif %}
retry:
automatic:
- exit_status: -1 # Agent was lost

1
requirements-dev.txt
View File

@ -16,6 +16,7 @@ pytest
pytest-forked
pytest-asyncio
pytest-rerunfailures
pytest-shard
httpx
einops # required for MPT
openai