huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Let's try non sharded gemma.

Browse Source
This commit is contained in:
Nicolas Patry 2024-10-09 16:37:10 +02:00
parent 15e178e3ad
commit 1e03ea96d0
No known key found for this signature in database
GPG Key ID: 64AF4752B2967863
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/build.yaml vendored
View File

@ -78,7 +78,7 @@ jobs:
# 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_simple" export extra_pytest="-k test_flash_gemma_simple"
;; ;;
esac esac
echo $dockerfile echo $dockerfile

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

@ -16,7 +16,7 @@ async def flash_gemma(flash_gemma_handle):
@pytest.mark.release @pytest.mark.release
@pytest.mark.asyncio @pytest.mark.asyncio
@pytest.mark.private @pytest.mark.private
async def test_flash_gemma(flash_gemma, response_snapshot): async def test_flash_gemma_simple(flash_gemma, response_snapshot):
response = await flash_gemma.generate( response = await flash_gemma.generate(
"Test request", max_new_tokens=10, decoder_input_details=True "Test request", max_new_tokens=10, decoder_input_details=True
) )