Inference
Free
vLLM
Adoption
GitHub forks
19.3K▲ 1.6%
GitHub stars
86K▲ 0.7%
PyPI / week
656.9K▲ 16.0%
Objective usage signals from public registries (Hugging Face, GitHub, npm, PyPI, Wikipedia), captured every 6 hours. Δ compares to ~7 days ago.
Why is this hot
21 mentions / 7d across 3 sources (diversity ×1.3)last 48h: 3 vs baseline 3.0/day
- High-Interactivity Decode with FlyDSL MonoKernels in vLLMhn
- Taking vLLM Apart: A Practical Guide to Disaggregated Servinghn
- Show HN: Production Grammar-Guided Decoding in vLLM with Xgrammar Benchmarkshn
- Show HN: TrnRT – An open-source LLM inference engine for AWS Trainiumhn
- Intel benchmarks D270 vs. RTX PRO 6000: 1.12x throughput on Qwen3-30B-A3B (vLLM)hn
Top mentions by weighted contribution (source authority × engagement × recency).
Description
High-throughput LLM serving engine.
Recent mentions in news (15)
- High-Interactivity Decode with FlyDSL MonoKernels in vLLMhn-ai · 1d
- Taking vLLM Apart: A Practical Guide to Disaggregated Servinghn-ai · 1d
- GateWatch: Low-Overhead LLM Monitoring with Boolean Circuitsarxiv-ai · 1d
- Show HN: Production Grammar-Guided Decoding in vLLM with Xgrammar Benchmarkshn-ai · 2d
- A Fast, Programmable GPU-to-CPU Invocation Layer for GPU-Initiated Communicationarxiv-ai · 2d
- Same Model, Different People: Numerical Execution Contracts and the Reproducibility of Fairness Auditsarxiv-ai · 2d
- Spool: Low-Latency Streaming Inference for Hybrid Vision-Language Modelsarxiv-ai · 2d
- Storing the Gemma 4 K=V Cache Once: Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernelsarxiv-ai · 2d
- Show HN: TrnRT – An open-source LLM inference engine for AWS Trainiumhn-ai · 2d
- LoopPrune: Recurrent Pruning for Looped Diffusion Transformersarxiv-ai · 2d
- LoopZip: Visual Token Compression for Efficient Looped Vision-Language Modelsarxiv-ai · 2d
- SpecSearch: Towards Hardware-Aware Efficient Speculative Decodingarxiv-ai · 3d
- Communicate the Change: Efficient Expert Parallelism via Activation Compressionarxiv-ai · 3d
- HyCoInfer: Cloud-Edge Collaborative Inference for Large Language Models on Heterogeneous GPU-FPGA Architecturesarxiv-ai · 3d
- Beyond Bitwidth: Deployment-Constrained Mixed-Precision Quantization for Multilingual LLM Inference on NVIDIA Blackwellarxiv-ai · 3d
Related Briefs & Stories (6)
—
1 items • 2dUnbriefed story cluster
—
1 items • 2dUnbriefed story cluster
—
1 items • 2dUnbriefed story cluster