- 🔭 I’m currently working on LiBai
- I'm learning cmu15213.
🤹♀️ Recent Blog
- W4A8KV4 Quantization Summary and Best Practices - Fri, 30 Aug 2024
- Low-Bit MoE Quantization for Large Language Models - Thu, 25 Jul 2024
- Speculative Sampling for Faster LLM Inference - Thu, 20 Jun 2024
- DeepSeek-v2 In a Nutshell - Multi-Head Latent Attention - Wed, 15 May 2024
- LayerNorm Mathematical Derivation and Implementation - Wed, 10 Apr 2024