[BugFix]add int8 cache dtype when using attention quantization #148
Triggered via pull request
February 21, 2025 02:52
Status
Failure
Total duration
3h 39m 38s
Artifacts
–
vllm_ascend_test.yaml
on: pull_request
vLLM Ascend test (self-host)
17m 7s
Annotations
1 error
vLLM Ascend test (self-host)
Process completed with exit code 1.
|