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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Performance][Pooling] Bulk-submit offline requests to avoid microbatch fragmentation
- Enable NVFP4 KV cache on SM120 (consumer Blackwell)
- [Bug]: KDA/gated-delta-rule chunked-scan buffers are outside memory profiling — runtime OOM at large --max-num-batched-tokens
- [RFC]: GDS kv offloading
- [Bugfix][Parser] Gemma4: parse tool calls whose opener omits the `call:` marker
- [Bugfix][Spec Decode] Honor configured tokenizer revisions in TLI mapping
- [Benchmarks] Add --include-multi-turn to ShareGPT, plus configurable prompt-length limits
- [Bug]: `--cpu-offload-gb` evicts in declaration order, which for MoE offloads the hottest weights first
- [Bug]: Qwen4Exp is gated off on XPU, but most of what the gate hides is not XPU-specific
- [Bugfix] Reap orphaned /dev/shm region files via flock-based liveness
- Docs
- Python not yet supported