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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Multimodal] fix: resolve memory allocation and buffer overflow in audio resampling
- [Bug]: glm-5-fp8 zcode str object has no attribute items
- [Attention][Quantization] NVFP4 KV cache on consumer/SoC Blackwell (sm120/sm121) for Gemma 3/4 via FlashInfer FA2
- [Bugfix][Core] Skip stale KV xfer finish notifications for already-freed requests
- [Docs] Add Qwen2.5-Coder-7B-Instruct to batch invariance tested models
- v1 P/D: _update_from_kv_xfer_finished AssertionError (kills EngineCore) when an aborted request's finished_recving + finished_sending land in the same step
- [Bugfix][Model] Add get_expert_mapping to GraniteMoeModel for LoRA support
- [Hybrid] Decoupling block_size from allocation block size
- [Bug]: Cross-node CUDA graph capture fails (illegal memory access at capture_end) — host-staged NCCL all-reduce captured by `breakable_cudagraph` on GB10 (no GPUDirect); `splitting_ops` not honored
- [Bug]: deepseek_v4 / deepseek_v32 tokenizers ignore add_generation_prompt and continue_final_message (silent empty/garbled output on assistant-terminated conversations)
- Docs
- Python not yet supported