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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Multimodal] Add TorchCodec image decoding backend
- [Bugfix][MRV2] Fix FULL profiling context
- [Bugfix][Frontend] Aggregate per-engine ORCA metrics under data parallel
- [Bugfix][Kernel] Apply one more decay step in lightning_attention prefill
- [Feature][Rust Frontend] Support scale-out request cancellation
- [RFC]: Reduce descriptor and WR overhead to improve Mooncake KV transfer bandwidth
- [Docs] Document kv_load_failure_policy in MooncakeStoreConnector guide
- [Bugfix][LoRA] Preserve idle DP adapters and remap MoE slots
- [Build] Let the NIXL source build take a Git ref and build the LIBFABRIC plugin
- [Bugfix][Core] Cover the first spec decode step in the full-sequence admission gate
- Docs
- Python not yet supported