Сейчас ищут
Neural Magic. Смотреть видео: VLLM Office Hours Advanced Techniques For Maximizing VLLM Performance September 19 2024, VLLM Office Hours Using NVIDIA CUTLASS For High Performance Inference September 05 2024, VLLM Office Hours VLLM On AMD GPUs And Google TPUs August 21 2024, VLLM Office Hours Multimodal Models In VLLM With Roblox August 8 2024.