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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: RunAI model streamer breaks in 0.11
- [ROCM] Add sinks argument to AiterFlashAttentionImpl
- [Bug]: (EngineCore_DP0 pid=77352) INFO 10-22 09:43:49 [shm_broadcast.py:466] No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-consuming work (e.g. compilation).
- [CI/Build] improve editable mode setup
- [perf] Optimize Qwen2-VL Startup Performance with LRU Cache
- [BugFix] Fix KV cache offload state inconsistency
- [BugFix] fix: skip check unstreamed tool arg tokens when tool call name is present
- [Bugfix] Potential Out-of-bounds in moe_align_sum_kernels.cu
- [torch.compile] Try using Dynamo-native padding
- [Bug]: reload_weights (via collective_rpc) Fails to Load Quantized Models Correctly, Causing Tensor Shape AssertionError
- Docs
- Python not yet supported