InternLM /xtuner
为超大规模 MoE 模型打造的新一代训练引擎
Python5221
qwen3-moe 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
为超大规模 MoE 模型打造的新一代训练引擎
RapidLLM is an LLM inference framework with continuous batching, tensor and data parallelism, quantized weights, and with pluggable Triton/CUDA kernels.
Qwen3 MoE Router Statistics | 큐웬3 MoE
Viby vibes everything.