squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI] Disable flash_attn backend for spec decode (#5286)

Browse Source
This commit is contained in:
Simon Mo 2024-06-05 17:49:27 -05:00 committed by GitHub
parent 8f1729b829
commit 3a6ae1d33c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.buildkite/test-pipeline.yaml
View File

@ -124,7 +124,10 @@ steps:
- label: Speculative decoding tests - label: Speculative decoding tests
#mirror_hardwares: [amd] #mirror_hardwares: [amd]
command: pytest -v -s spec_decode commands:
# See https://github.com/vllm-project/vllm/issues/5152
- export VLLM_ATTENTION_BACKEND=XFORMERS
- pytest -v -s spec_decode
- label: LoRA Test %N - label: LoRA Test %N
#mirror_hardwares: [amd] #mirror_hardwares: [amd]