We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent c57226b commit 63a6069Copy full SHA for 63a6069
.github/workflows/float8_test.yml
@@ -29,7 +29,7 @@ jobs:
29
gpu-arch-type: "cuda"
30
gpu-arch-version: "12.6"
31
- name: H100
32
- runs-on: linux.aws.h100
+ runs-on: linux.aws.h100.4
33
torch-spec: '--pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu126'
34
35
gpu-arch-version: "12.4"
@@ -53,6 +53,4 @@ jobs:
53
uv pip install -r dev-requirements.txt
54
uv pip install vllm
55
pip install .
56
- pytest test/float8 --verbose -s
57
- pytest test/integration --verbose -s
58
- pytest test/dtypes/test_affine_quantized_float.py --verbose -s
+ ./test/float8/test_everything.sh
0 commit comments