huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Intel CI ?

Browse Source
This commit is contained in:
Nicolas Patry 2024-10-09 16:08:03 +02:00
parent 43f39f6894
commit 15e178e3ad
No known key found for this signature in database
GPG Key ID: 64AF4752B2967863
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/build.yaml vendored
View File

@ -75,10 +75,10 @@ jobs:
export label_extension="-intel-cpu" export label_extension="-intel-cpu"
export docker_devices="none" export docker_devices="none"
export docker_volume="/mnt/cache" export docker_volume="/mnt/cache"
export runs_on="ubuntu-latest" # export runs_on="ubuntu-latest"
# 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_llama_load" export extra_pytest="-k test_flash_llama_simple"
;; ;;
esac esac
echo $dockerfile echo $dockerfile

2
integration-tests/models/test_flash_llama.py
View File

@ -15,7 +15,7 @@ async def flash_llama(flash_llama_handle):
@pytest.mark.asyncio @pytest.mark.asyncio
@pytest.mark.private @pytest.mark.private
async def test_flash_llama(flash_llama, response_snapshot): async def test_flash_llama_simple(flash_llama, response_snapshot):
response = await flash_llama.generate( response = await flash_llama.generate(
"Test request", max_new_tokens=10, decoder_input_details=True "Test request", max_new_tokens=10, decoder_input_details=True
) )