vllm-project projects
Search results
35 open and 0 closed projects found.
Sprint on DFlash+DSpark speculative decoding model support and performance.
#58 updated Sep 12, 2026
PRs and issues related to NVIDIA hardware
#31 updated Sep 12, 2026
torch.compile integration related
#12 updated Sep 12, 2026
Tracks Ray issues and pull requests in vLLM
#7 updated Sep 12, 2026
Track the agentic-api MVP: harness support first, then protocol parity, reliability, deployment, and longer-term performance work.
#52 updated Sep 11, 2026
Tracking failures that are occurring in CI.
#20 updated Sep 11, 2026
Work on the Transformers modeling backend: running Transformers model implementations inside vLLM.
#28 updated Sep 11, 2026
Open tracking AMD ROCm CI failures and fixes for vLLM.
#39 updated Sep 11, 2026
Maintainer's tracking board for Prometheus metrics related PRs and issues
#44 updated Sep 11, 2026
2025-02-25: DeepSeek V3/R1 is supported with optimized block FP8 kernels, MLA, MTP spec decode, multi-node PP, EP, and W4A16 quantization
#5 updated Sep 10, 2026
Community requests for multi-modal models
#10 updated Sep 10, 2026
Track CPU related issues & tasks
#42 updated Sep 9, 2026
Optimization and bugfixes for Qwen3.5 model series.
#50 updated Sep 9, 2026
Main tasks for the multi-modality workstream (#4194)
#8 updated Sep 2, 2026
A list of onboarding tasks for first-time contributors to get started with vLLM.
#6 updated Aug 30, 2026
Backlog for CI feature requests
#35 updated May 8, 2026
You can’t perform that action at this time.