vLLM

Objective usage signals from public registries (Hugging Face, GitHub, npm, PyPI, Wikipedia), captured every 6 hours. Δ compares to ~7 days ago.

• AsmEvo: Agentic Assembly-Level Optimization of AMD GPU Kernels with Functional Equivalence Verification
  arxiv-ai · 3d
• Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures
  arxiv-ai · 4d
• Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM services
  arxiv-ai · 5d
• New OllamaMQ v0.3.0
  hn-ai · 5d
• Native vLLM and ROCm 7.15 for RX 6000 (RDNA2) on Windows 11 – 26 Tflops FP16
  hn-ai · 6d
• ArguLens: An Open-Source System for Automated Essay Scoring and Label-Aware Feedback Generation
  arxiv-ai · 6d
• Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN
  arxiv-ai · 7d
• Beyond Binary Priorities: Multi-Tier SLA Scheduling for Large Language Model Serving
  arxiv-ai · 7d
• Engineering Signals of Human-AI Collaboration in the Agentic Coding Era: A Longitudinal Analysis of 33,228 Pull Requests from vLLM and SGLang with Implications for Biomedical AI Agents and Bioinformatics Pipeline Developmen
  arxiv-ai · 10d
• The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference
  arxiv-ai · 10d
• Show HN: NanoRL – RL training for LLMs in ~1,800 lines
  hn-ai · 11d
• vToken: Token-Level Virtualization for Reclaimable KV Caches
  arxiv-ai · 11d
• Trie Automata for Constrained Decoding over Large Finite Sets
  arxiv-ai · 11d
• Ask HN: Are there any production LLM pipeline setups to learn from?
  hn-ai · 11d
• Scheduling Mixed RL Rollouts Beyond Prefix Locality
  arxiv-ai · 12d