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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][Frontend] Add opt-in incremental prompt-encoding cache for multi-turn chat
- [Spec Decode][Perf] Rowwise-fp8 draft lm_head for DSpark (opt-in)
- [Bugfix][Kernel] Zero TRT-LLM 8x4 FP4 scale padding
- fix: aggressively zero speculator buffers to prevent CUDA illegal memory access on H100
- Revert "Support nvfp4 kv with kv-cache-dtype-skip-layers sliding_window" (#42890)
- CUDA illegal memory access during speculator prefill CUDA graph capture on H100
- [V1][Sampling] Add opt-in fused generated-token top-logprobs path
- [Bug]: ValueError: The supplied chat template string (examples/tool_chat_template_gemma4.jinja) appears path-like
- [Bug]: wrong cutlass Arch import
- [Bugfix] Treat tool parameter schemas without a type as allowing any type
- Docs
- Python not yet supported