mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-23 19:00:21 +08:00

History

[Sampler] Support returning final logprobs (#22387 )

Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2025-08-20 21:28:32 -07:00

faq.md

Stop using title frontmatter and fix doc that can only be reached by search (#20623 )

2025-07-08 03:27:40 -07:00

metrics.md

…

README.md

[Docs] Improve docs navigation (#22720 )

2025-08-12 04:25:55 -07:00

reproducibility.md

…

security.md

[Docs] Switch to better markdown linting pre-commit hook (#21851 )

2025-07-29 19:45:08 -07:00

troubleshooting.md

[Frontend] Expose do_log_stats interval to env (#22905 )

2025-08-15 13:00:20 +00:00

usage_stats.md

…

v1_guide.md

[Sampler] Support returning final logprobs (#22387 )

2025-08-20 21:28:32 -07:00

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.