I mapped the KLD of KV cache quantization for Qwen3.6-35B-A3B and Gemma4-E2B QAT (opens in new tab)
pixi recipes for local LLM stack. Contribute to crusaderky/pixi-llm-recipes development by creating an account on GitHub.
Read the original articlepixi recipes for local LLM stack. Contribute to crusaderky/pixi-llm-recipes development by creating an account on GitHub.
Read the original article