Set FP16 KV-cache for non-quantized text models #5264
Triggered via pull request
November 29, 2024 12:22
Status
Cancelled
Total duration
2m 44s
Artifacts
–
Annotations
4 errors
build (2.4.*)
Canceling since a higher priority waiting request for 'INC - Test-ak/fp16_cache_for_fp16_models' exists
|
build (2.4.*)
The operation was canceled.
|
build (2.5.0)
Canceling since a higher priority waiting request for 'INC - Test-ak/fp16_cache_for_fp16_models' exists
|
build (2.5.0)
The operation was canceled.
|