Dev

6 repos

• ★ 255 huawei-csl/KVarN Python new · 7d old
  KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
  agentic-ai kv-cache llm llm-inference long-context quantization vllm homepage ↗
• ★ 69 seanmor5/honeycomb Elixir
  Fast LLM inference with Elixir and Bumblebee
• ★ 2.7k walkinglabs/hands-on-modern-rl Python
  🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
  agent agentic agentic-ai agentic-rl dpo grpo llm homepage ↗
• ★ 219 nick7nlp/Awesome-LLM-On-Policy-Distillation Python
  A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
  awesome-list awesome-opd awesomeopd github-pages knowledge-distillation large-language-models llm
• ★ 1.5k radixark/miles Python
  Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
• ★ 60k earendil-works/pi TypeScript
  AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods