mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-12 04:44:52 +00:00
Flash llama on intel CPU ?
This commit is contained in:
parent
8321a6c8e5
commit
46ccffd246
2
.github/workflows/build.yaml
vendored
2
.github/workflows/build.yaml
vendored
@ -77,7 +77,7 @@ jobs:
|
|||||||
export docker_volume="/mnt/cache"
|
export docker_volume="/mnt/cache"
|
||||||
export runs_on="aws-highmemory-32-plus-priv"
|
export runs_on="aws-highmemory-32-plus-priv"
|
||||||
export platform="cpu"
|
export platform="cpu"
|
||||||
export extra_pytest="-k test_flash_gemma_gptq_load"
|
export extra_pytest="-k test_flash_llama_load"
|
||||||
;;
|
;;
|
||||||
esac
|
esac
|
||||||
echo $dockerfile
|
echo $dockerfile
|
||||||
|
Loading…
Reference in New Issue
Block a user