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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][RDNA][Perf] Bump triton_kernels to ROCm 3.8.x with the RDNA MXFP4 configs
- [Bug][ROCm] GLM-5.3 TP8 hangs during OffloadingConnector CPU-GPU copies when other vLLM processes share the MI325X SR-IOV VFs (v0.32.0)
- [Model] Quantize Muse Spark BF16 routed experts with online nvfp4_per_token
- [Bug]: [ROCm/MI250] Qwen3.8-Flash-Next worker SIGABRT in HIP async event thread: free(): invalid next size (fast)
- [Perf][Attention] Cache FlashAttention K/V cache views per tensor
- [Bugfix][Frontend] Send `usage: null` on stream chunks when `include_usage` is set
- [Bugfix][ROCm][KV Connector] MoRIIO: fix port collision with TP > 1 and DP > 1
- [Bugfix][Whisper] Raise default max_num_batched_tokens to fit the encoder input
- [MoE] Load fused expert weights with one weight_loader call per shard
- [Core] Don't let a second SIGTERM interrupt EngineCore and worker teardown
- Docs
- Python not yet supported