Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/model-workflows/shared-cache.md
Original file line number Diff line number Diff line change
Expand Up @@ -190,9 +190,9 @@ cross-user NFS and actual model loading remain separate validation gates.
- [CLI guide](https://huggingface.co/docs/huggingface_hub/v2.1.1/en/guides/cli),
[environment variables](https://huggingface.co/docs/huggingface_hub/v2.1.1/en/package_reference/environment_variables),
[cache layout](https://huggingface.co/docs/huggingface_hub/v2.1.1/en/guides/manage-cache).
- [vLLM v0.31.0](https://github.com/vllm-project/vllm/releases/tag/v0.31.0)
- [vLLM v0.32.0](https://github.com/vllm-project/vllm/releases/tag/v0.32.0)
is the serving release observed on this date; its
[requirements](https://github.com/vllm-project/vllm/blob/v0.31.0/requirements/common.txt)
[requirements](https://github.com/vllm-project/vllm/blob/v0.32.0/requirements/common.txt)
specify `huggingface_hub >= 1.31.0`. This cache change neither installs vLLM
nor claims a tested serving combination. Re-check and validate the serving
environment separately; a minimum requirement is not compatibility evidence.
16 changes: 8 additions & 8 deletions docs/model-workflows/vllm-quickstart.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ is needed. Review the model license before use.
in a login shell outside your allocation. Do not override `CUDA_VISIBLE_DEVICES`
to reach other GPUs. This guide does not allocate resources or install drivers.
- A driver compatible with the selected vLLM wheel's CUDA runtime. The tagged
v0.31.0 NVIDIA guide describes CUDA 12.9 wheels and compute capability 7.5+.
v0.32.0 NVIDIA guide describes CUDA 13.0 (default) and 12.9 wheels and compute capability 7.5+.
Check the upstream installation guide for your GPU/driver before installing;
a working `nvidia-smi` alone does not establish wheel compatibility.
- Python **3.12** with venv support, the Python 3.12 development headers and a C
Expand Down Expand Up @@ -56,9 +56,9 @@ python3.12 -m venv "$HOME/.venvs/deepops-vllm"
"$HOME/.venvs/deepops-vllm/bin/vllm" --version
```

The example pins vLLM **0.31.0**, licensed under **Apache-2.0** (verified on
2026-10-07 against the [tagged license](https://github.com/vllm-project/vllm/blob/v0.31.0/LICENSE)
and [package metadata](https://pypi.org/project/vllm/0.31.0/)). This is the serving
The example pins vLLM **0.32.0**, licensed under **Apache-2.0** (verified
2026-10-07 (0.31.0) and rechecked for 0.32.0 against the [tagged license](https://github.com/vllm-project/vllm/blob/v0.32.0/LICENSE)
and [package metadata](https://pypi.org/project/vllm/0.32.0/)). This is the serving
package's license, not the model's or every dependency's. Transitive packages
are not a full lockfile: record `pip freeze` with validation evidence, and use
your site's reviewed wheel set for repeatable deployment. Do not mix an existing
Expand Down Expand Up @@ -210,8 +210,8 @@ It is not installed, required, or validated by this example.

## Primary sources (checked 2026-10-05)

- [vLLM 0.31.0 package metadata](https://pypi.org/project/vllm/0.31.0/).
- Tagged [GPU requirements](https://github.com/vllm-project/vllm/blob/v0.31.0/docs/getting_started/installation/gpu.md)
and [NVIDIA installation details](https://github.com/vllm-project/vllm/blob/v0.31.0/docs/getting_started/installation/gpu.cuda.inc.md).
- Tagged [OpenAI-compatible server guide](https://github.com/vllm-project/vllm/blob/v0.31.0/docs/serving/online_serving/openai_compatible_server.md).
- [vLLM 0.32.0 package metadata](https://pypi.org/project/vllm/0.32.0/).
- Tagged [GPU requirements](https://github.com/vllm-project/vllm/blob/v0.32.0/docs/getting_started/installation/gpu.md)
and [NVIDIA installation details](https://github.com/vllm-project/vllm/blob/v0.32.0/docs/getting_started/installation/gpu.cuda.inc.md).
- Tagged [OpenAI-compatible server guide](https://github.com/vllm-project/vllm/blob/v0.32.0/docs/serving/online_serving/openai_compatible_server.md).
- [Shared-cache sources and writer pin](shared-cache.md#primary-sources-verified-2026-10-05).
2 changes: 1 addition & 1 deletion examples/vllm/requirements.txt
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
# Install in a private Python 3.12 environment, separate from Ansible and the cache writer.
vllm==0.31.0
vllm==0.32.0
2 changes: 1 addition & 1 deletion scripts/validation/tests/test_finetune_readiness.py
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ def run_command(self, command, timeout):
return 0, "--container-image --container-mounts", ""
if command[0] == "srun" and "--gpus=1" in command:
return 0, self.smoke_output, ""
self.fail("unexpected command: " + repr(command))
raise AssertionError("unexpected command: " + repr(command))

def validate(self):
with patch.object(self.validator, "run", side_effect=self.run_command):
Expand Down
Loading