vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Frontend] Set completed_at on completed Responses
- [Perf][Core] Add sha256_int32 prefix-cache hash over int32 token buffers
- [Bugfix][Frontend] Start the chat template render timeout when the render starts
- [Bugfix][Mooncake] Invalidate unattempted KV blocks after split-load failures
- [Bugfix][Benchmark] Reject colliding sweep figure filenames
- [Bugfix][Benchmark] Support quoted commas in sweep plot filters
- [Feature]: Run Nemotron 3.5 Super VL without the --trust-remote-code flag
- [Bugfix][GLM] Preserve kpool history at unaligned prefill boundaries
- [Bugfix] Fail fast on incomplete local checkpoints; name the layer in the NVFP4 scale error
- Optimize TP MoE collectives via output projection sharding
- Docs
- Python not yet supported