This website requires JavaScript.
Explore
Help
Sign In
youngkingdom
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
4555143ea7fdd2b2f0106e40889bfbab49879237
vllm
/
docs
/
usage
History
Li, Jiang
4555143ea7
[CPU] V1 support for the CPU backend (
#16441
)
2025-06-03 18:43:01 -07:00
..
faq.md
[Doc] Reorganize user guide (
#18661
)
2025-05-24 07:25:33 -07:00
metrics.md
[V1][Metrics] Remove metrics that were deprecated in 0.8 (
#18837
)
2025-05-28 18:54:12 +00:00
README.md
[Doc] Reorganize user guide (
#18661
)
2025-05-24 07:25:33 -07:00
reproducibility.md
[Doc] Update reproducibility doc and example (
#18741
)
2025-05-27 07:03:13 +00:00
security.md
[doc] fix the list rendering issue - security.md (
#18982
)
2025-05-31 10:39:21 +00:00
troubleshooting.md
[Doc] Reorganize user guide (
#18661
)
2025-05-24 07:25:33 -07:00
usage_stats.md
[Doc] Reorganize user guide (
#18661
)
2025-05-24 07:25:33 -07:00
v1_guide.md
[CPU] V1 support for the CPU backend (
#16441
)
2025-06-03 18:43:01 -07:00
README.md
Using vLLM
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.