mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 20:04:59 +08:00

History

Mark McLoughlin 2dcbac9077

[Docs] Generate full list of metrics in user docs (#30388 )

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2025-12-10 16:09:34 +00:00

faq.md

…

metrics.md

[Docs] Generate full list of metrics in user docs (#30388 )

2025-12-10 16:09:34 +00:00

README.md

[Doc] Fix failing doc build (#28772 )

2025-11-15 05:33:27 -08:00

reproducibility.md

[Doc] Update more docs with respect to V1 (#29188 )

2025-11-23 10:58:48 +08:00

security.md

[Docs] Discuss api key limitations in security guide (#29922 )

2025-12-02 20:57:28 -08:00

troubleshooting.md

[doc] add guide about the provided PTX was compiled with an unsupported toolchain (#28305 )

2025-11-08 00:26:34 +08:00

usage_stats.md

…

v1_guide.md

[Doc] Update more docs with respect to V1 (#29188 )

2025-11-23 10:58:48 +08:00

README.md

Using vLLM

First, vLLM must be installed for your chosen device in either a Python or Docker environment.

Then, vLLM supports the following usage patterns:

Inference and Serving: Run a single instance of a model.
Deployment: Scale up model instances for production.
Training: Train or fine-tune a model.