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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: vLLM hangs when sending a request with "response_format" key for early unsuppoted models like Minimax-M2.5
- [Perf] Add tuned Triton fused MoE configs for NVIDIA H20 (fp8_w8a8)
- [Feature]: Could you help with implement the KV cache pruning feature on vLLM?
- [KVCache] Support model specific KVCache planning
- Add DeepSeek-V4 FIM completion rendering
- [Bugfix] Fix speculative decoding for short_conv (LFM2) models
- [Bug]: [Bug] Severe GPU Memory Leak and OOM with Native KV Offloading in Multi-Node PP=2 TP=8 Setup (v0.22.0)
- [Bug]: when set kv_cache_dtype to fp8 or fp8_e4m3 causes the d node to crash
- [Bug]: vLLM hangs during speculative decoding with MoE draft model near max_model_len under Data Parallelism (DP)
- [Draft][XPU] Initial enablement deepep on XPU
- Docs
- Python not yet supported