NVIDIA DGX Spark In-Depth Review: A New Standard for Local AI Inference

Deploying DeepSeek on 96 H100 GPUs

Chat arena for crowd sourcing model evaluation

Gpt2-Chatbot Removed from Lmsys

Mistral AI launches Mixtral-Next

Fast and Expressive LLM Inference with RadixAttention and SGLang

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Beating GPT-4 with a 13B model

LLM Leaderboard

How long can open-source LLMs truly promise on context length?

Chatbot Arena Leaderboard

Vicuna: An Open-Source Chatbot Impressing GPT-4

LLMs Leaderboard

Chatbot Arena: Benchmarking LLMs in the Wild with Elo Ratings

Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality