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
- [Bug] DFlash on SM121 (GB10 / DGX Spark): attention autoselect picks FLASH_ATTN for non-causal draft attention and device-asserts in _vllm_fa2_C.varlen_fwd
- [Bugfix] benchmark_moe: do not abort tuning when a candidate config fails Triton compilation
- [Bug]: With qwen3.5-35b-a3b, the performance is relatively poor both when using dflash and when not using it, but the accepted length of dflash is around 5–6.
- [PD] Emit inactive KV blocks for decode affinity
- [Spec Decode][Perf] Optimize DSpark Markov head with addmm
- [Bugfix][Core] Fix invalid block handling for hybrid KV cache groups
- [Doc] Add ARM+NVIDIA GB10 embedding notes to GPU CUDA installation
- [Bug]: DeepSeek-V4-Flash-0731 + DSpark fails on RTX PRO 6000 (SM120) with FlashInfer sparse MLA decode kernel routing
- [Bugfix][Model] Kimi-K3 NVIDIA: delegate regular FusedMoE padding to the selected quantization backend
- [Feature]: Kimi K3 Performance Optimization
- Docs
- Python not yet supported