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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Installation]: old nccl version in docker container
- [LoRA] Integrate flashinfer MoE LoRA
- fix(deepseek_v4): resolve auto kv-cache-dtype to fp8_ds_mla on SM120
- Revert "[Platform] Replace `torch.cuda.mem_get_info` with `torch.accelerator.get_memory_info`" (#44825)
- [KVOffload] Document CPU eviction behavior as reference (control branch)
- [Bug]: 较高版本 Transformers 与已知 Mindformers YAML 配置冲突,导致 AISBench 测试报错 TypeError: Can't instantiate abstract class MindformersTokenizer
- [Feature]: Support for Keye-VL-2.0-30B-A3B
- [Bug]:DeepSeek-V4-Flash (TP=4) worker dies with no traceback during a ~8s runtime TileLang recompile of mhc_pre_big_fuse_with_norm_tilelang
- fix(security): validate g_idx bounds in CPU WNA16 GPTQ desc_act kernel
- [ROCm][MiniMax-M3] Fuse input-side all-reduce + RMSNorm in the AMD decoder
- Docs
- Python not yet supported