Skip to content

[BugFix]add int8 cache dtype when using attention quantization #143

[BugFix]add int8 cache dtype when using attention quantization

[BugFix]add int8 cache dtype when using attention quantization #143

Triggered via pull request February 21, 2025 02:11
Status Failure
Total duration 2m 51s
Artifacts

mypy.yaml

on: pull_request
Matrix: mypy
Fit to window
Zoom out
Zoom in

Annotations

8 errors
mypy (3.10): vllm_ascend/worker.py#L112
Name "cache_config" is not defined [name-defined]
mypy (3.10)
Process completed with exit code 1.
mypy (3.12)
The job was canceled because "_3_10" failed.
mypy (3.12)
The operation was canceled.
mypy (3.11)
The job was canceled because "_3_10" failed.
mypy (3.11)
The operation was canceled.
mypy (3.9)
The job was canceled because "_3_10" failed.
mypy (3.9)
The operation was canceled.