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
- [Security] Validate cache_salt length and charset before engine hashing
- [Performance]: 3.4 s engine stalls from DeepGEMM compiling the o-projection kernel per prefill chunk size, DeepSeek-V4.1-Flash on 8x B200
- [Perf][Attention] DeepSeek-V4.1-Flash offline throughput on 8 x B200: 24.60 s to 22.84 s per 1000 requests at TP=8, mostly from sparse-attention candidate-block kernels sized by the 1M-token limit
- [Bugfix][Weight Transfer] Preserve tied parameter names in ModuleSource
- [Bugfix][Multimodal] Normalize single-channel audio to 1D
- [Kernel][CI] Enable --jit-monitor-mode error on CI for DSv4, Gemma4 and gpt-oss
- [Perf][Marlin] Reduce DS V4.1 Flash MoE padding on SM90
- [Bugfix][Core] Profile and validate kv_cache_memory_bytes instead of skipping the profile
- [SM120] Field report: running DeepSeek-V4.1-Flash end-to-end on 8x RTX PRO 6000 — pitfall map + working configuration (1M context verified)
- [RFC][KV Offload]: Align sliding-window restore coverage with MTP-retained history
- Docs
- Python not yet supported