工具NVIDIA TensorRT-LLM · v1.4.0rc3NVIDIA · 11-07 05:38Highlights Known Issues DSA models, including GLM-5.2, may produce incorrect output when using an NVFP4 KV cache. Kimi K3 DSpark with MegaMoE CuTe DSL TEP and CUDA graphs may hang关注方向软件、模型、AI未读查看原文 ↗