helloericsf

Better than DeepSeek R1? MiniMax-M1:open-weight hybrid-attention reasoning model

kit - Code Intelligence Toolkit

DeepSeek Open Source Optimized Parallelism Strategies, 3 repos

DeepSeek Open Source DeepGEMM – FP8 GEMM Library(300 lines for 1350+ FP8 TFLOPS)

Alibaba Open Source Large-Scale Video Generative Models: Wan2.1

DeepSeek open source DeepEP – library for MoE training and Inference

DeepSeek Open Source FlashMLA – MLA Decoding Kernel for Hopper GPUs

New Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarks

Longest context up to 4M, MiniMax-01 hybrid 456B Open source model

DeepSeek v3 beats Claude sonnet 3.5 and way cheaper

NeurIPS and Dr. Picard released statement for singling out Chinese scholars

Tencent Hunyuan-Large