AI Inference / Inference Microservices – NVIDIA Technical Blog http://www.open-lab.net/ko-kr/blog Thu, 15 May 2025 03:31:08 +0000 ko-KR hourly 1 NVIDIA ??? ???? ?? AI ?? ?? ??? http://www.open-lab.net/ko-kr/blog/optimize-ai-inference-performance-with-nvidia-full-stack-solutions/ Thu, 15 May 2025 03:31:05 +0000 http://www.open-lab.net/ko-kr/blog/?p=3729 Reading Time: 5 minutes 2025? 3? 18??? NVIDIA Triton Inference Server? ?? NVIDIA Dynamo? ??? ???????. AI ?? ??????? ???? ???, ??? ?? ??? ?? ??? ? ?? ???? ??? ??? ???? ?? ???? AI ??? ???? ?? ?? ??? ?? ????. NVIDIA? ?, ???, ?????? ??? ??? ??? ?? ????? AI ???? ????? ???? ??? ??? ??? ? … Continued]]> Reading Time: 5 minutes 2025? 3? 18??? NVIDIA Triton Inference Server? ?? NVIDIA Dynamo? ??? ???????. AI ?? ??????? ???? ???, ??? ?? ??? ?? ??? ? ?? ???? ??? ??? ???? ?? ???? AI ??? ???? ?? ?? ??? ?? ????. NVIDIA? ?, ???, ?????? ??? ??? ??? ?? ????? AI ???? ????? ???? ??? ??? ??? ? ??? ???? ????, ??? AI ??? ? ?? ??? ? ???, ?????, ?? ???????. ???? ?? ?? ??? ?? ??? ??? ?????.

Source

]]> 3729 NVIDIA, Meta Llama 4 Scout ? Maverick??? ?? ??? http://www.open-lab.net/ko-kr/blog/nvidia-accelerates-inference-on-meta-llama-4-scout-and-maverick/ Wed, 16 Apr 2025 01:47:32 +0000 http://www.open-lab.net/ko-kr/blog/?p=3692 Reading Time: 3 minutes ?? ??? ??? Llama AI ??? ?? ??, Llama 4 Scout? Llama 4 Maverick? ??? ??????. NVIDIA? ???? ?????? ???? Blackwell B200 GPU??? ?? 4? ?? ??? ??? ? ??? ?? NVIDIA NIM ????????? ?? ???? ? ????. Llama 4 ??? ?? ????? ????? ??? ??? ????, ??? ??(MoE) ??? ?????. ??? ???? ??? ?? … Continued]]> Reading Time: 3 minutes ?? ??? ??? Llama AI ??? ?? ??, Llama 4 Scout? Llama 4 Maverick? ??? ??????. NVIDIA? ???? ?????? ???? Blackwell B200 GPU??? ?? 4? ?? ??? ??? ? ??? ?? NVIDIA NIM ????????? ?? ???? ? ????. Llama 4 ??? ?? ????? ????? ??? ??? ????, ??? ??(MoE) ??? ?????. ??? ???? ??? ?? Llama 4? ??? ??, ??, ???? ?? ???? ?? ? ???? ???? ??? ??? ??? ? ??? ?????. Llama 4 Scout? 1090? ??…

Source

]]> 3692 Spotlight: NVIDIA TensorRT-LLM? ??? NAVER Place? SLM Vertical Service ?? ???? http://www.open-lab.net/ko-kr/blog/spotlight-naver-place-optimizes-slm-based-vertical-services-with-nvidia-tensorrt-llm/ Wed, 12 Mar 2025 05:49:01 +0000 http://www.open-lab.net/ko-kr/blog/?p=3592 Reading Time: 7 minutes NAVER Place??? Place ??? ??? SLM Vertical Service? ???? ???? ???? ??(????, ??, ??)? ???? ???? ????.  ? ???? NVIDIA? NAVER? SLM Vertical Service ??? ?? TensorRT-LLM ?? ???? ??? Triton server? ??? ?? ???? ???? ??? ???? ????. ??? ???? ?? ??? ?????. ???? ???? Introduction to NAVER Place AI Development Team? ??????.  NAVER … Continued]]> Reading Time: 7 minutes NAVER Place??? Place ??? ??? SLM Vertical Service? ???? ???? ???? ??(????, ??, ??)? ???? ???? ????. ? ???? NVIDIA? NAVER? SLM Vertical Service ??? ?? TensorRT-LLM ?? ???? ??? Triton server? ??? ?? ???? ???? ??? ???? ????. ??? ???? ?? ??? ?????. ???? ???? Introduction to NAVER Place AI Development Team? ??????. SLM?? ?? ?? ??(LLM)? ?? ????? ?? ?? ?????…

Source

]]> 3592 DeepSeek-R1 ? ?? ?? ????? ?? GPU ?? ?? ??? http://www.open-lab.net/ko-kr/blog/automating-gpu-kernel-generation-with-deepseek-r1-and-inference-time-scaling/ Thu, 13 Feb 2025 15:30:09 +0000 http://www.open-lab.net/ko-kr/blog/?p=3506 Reading Time: 4 minutes AI ??? ?? ? ??? ??? ???? ?? ??? ?????, ??? ?? ?? ?? ?? ?? ????? ??? ???? ????. ? ??? AI? ?? ?? ???? ??? ???? ???? ?? ?? ??? ??? ??? ?, ?? ??? ???? ?????? ??? ??? ????? ?????. ?? ?? AI? ??? ??? ??? ???? ???? ??? ????, ????? ???? … Continued]]> Reading Time: 4 minutes AI ??? ?? ? ??? ??? ???? ?? ??? ?????, ??? ?? ?? ?? ?? ?? ????? ??? ???? ????. ? ??? AI? ?? ?? ???? ??? ???? ???? ?? ?? ??? ??? ??? ?, ?? ??? ???? ?????? ??? ??? ????? ?????. ?? ?? AI? ??? ??? ??? ???? ???? ??? ????, ????? ???? ???? ?? ? ????. ? ???? NVIDIA ?????? ?? ?? ?? ?? ? ??? DeepSeek-R1 ??? ?? ???? ?? ??? ??? ?? ??? ??? ??? ??? ??? ?? ??????. ? ??? ??? ????…

Source

]]> 3506 OpenAI Triton, NVIDIA Blackwell?? AI ?? ? ??????? ?? http://www.open-lab.net/ko-kr/blog/openai-triton-on-nvidia-blackwell-boosts-ai-performance-and-programmability/ Fri, 07 Feb 2025 06:42:28 +0000 http://www.open-lab.net/ko-kr/blog/?p=3469 Reading Time: 3 minutes ?? ??? ??? ????? ?? AI ????? ??? ?????. NVIDIA cuDNN? ?? ?????? ??? ???? ??? ????, CUTLASS? ?? ?????? ?? ?? ?????? ??? ?????. ??? ?? ???? ???? ??? ???????? ?? ?? ?? ??? ???? ??? ???. ???? Triton ????? NVIDIA Blackwell ?????? ??? ??? ????, Blackwell? ?? ??? ???? ????? ??? ?? ?????. … Continued]]> Reading Time: 3 minutes ?? ??? ??? ????? ?? AI ????? ??? ?????. NVIDIA cuDNN? ?? ?????? ??? ???? ??? ????, CUTLASS? ?? ?????? ?? ?? ?????? ??? ?????. ??? ?? ???? ???? ??? ???????? ?? ?? ?? ??? ???? ??? ???. ???? Triton ????? NVIDIA Blackwell ?????? ??? ??? ????, Blackwell? ?? ??? ???? ????? ??? ?? ?????. NVIDIA? OpenAI? ???? ?? ??, Triton ????? ?? NVIDIA Blackwell ????? ?????.

Source

]]> 3469 NVIDIA TensorRT-LLM, ????? ??? ???-??? ?? ??? http://www.open-lab.net/ko-kr/blog/nvidia-tensorrt-llm-now-accelerates-encoder-decoder-models-with-in-flight-batching/ Fri, 13 Dec 2024 06:46:20 +0000 http://www.open-lab.net/ko-kr/blog/?p=3368 Reading Time: 3 minutes NVIDIA? ?? NVIDIA TensorRT-LLM? ???-??? ?? ????? ?????? ??????. TensorRT-LLM? ??? ?? ??? ?? ????? ?? ??? ????? ?? ?? ????????. ???-??? ?? ??? ??? TensorRT-LLM? ??? ?? ????, NVIDIA GPU?? ?? ???? ??? AI ?? ??? ?? ??? ???? ??? ?????. TensorRT-LLM? NVIDIA TensorRT ??? ????? ?????. ???? LLM ?? ??? ?? ??? ??? … Continued]]> Reading Time: 3 minutes NVIDIA? ?? NVIDIA TensorRT-LLM? ???-??? ?? ????? ?????? ??????. TensorRT-LLM? ??? ?? ??? ?? ????? ?? ??? ????? ?? ?? ????????. ???-??? ?? ??? ??? TensorRT-LLM? ??? ?? ????, NVIDIA GPU?? ?? ???? ??? AI ?? ??? ?? ??? ???? ??? ?????. TensorRT-LLM? NVIDIA TensorRT ??? ????? ?????. ???? LLM ?? ??? ?? ??? ??? ????? ??? ??? ?? ?? ??? ??? ???? ????. ??…

Source

]]> 3368 NVSwitch? TensorRT-LLM ????? 3? ?? AllReduce ?? http://www.open-lab.net/ko-kr/blog/3x-faster-allreduce-with-nvswitch-and-tensorrt-llm-multishot/ http://www.open-lab.net/ko-kr/blog/3x-faster-allreduce-with-nvswitch-and-tensorrt-llm-multishot/#respond Fri, 15 Nov 2024 05:54:47 +0000 http://www.open-lab.net/ko-kr/blog/?p=3278 Reading Time: 3 minutes ??? ?? ?? ??? ??? ??? ???? ? ??? ?? ??? ??? ?? ???? ???? ??? AI ????? ???? ?? ?? ???? ????. ?? ???? ?? ?? ???? ????? GPU ??? ??? ??? ???? ?? GPU ??? ??????. ???? ??? ??? ?? NVIDIA NVLink Switch? ??? ?? ??? ?? 3??? ??? ??? ?? GPU ?? … Continued]]> Reading Time: 3 minutes ??? ?? ?? ??? ??? ??? ???? ? ??? ?? ??? ??? ?? ???? ???? ??? AI ????? ???? ?? ?? ???? ????. ?? ???? ?? ?? ???? ????? GPU ??? ??? ??? ???? ?? GPU ??? ??????. ???? ??? ??? ?? NVIDIA NVLink Switch? ??? ?? ??? ?? 3??? ??? ??? ?? GPU ?? ????, TensorRT-LLM ???? ?????. ? ?????? ? ??? ?? ?? GPU ??? ??? ??? ????? ??? ?????. ?? ??? ?? ??? ???? ?? GPU? ??? ??? ???? ?? GPU…

Source

]]> http://www.open-lab.net/ko-kr/blog/3x-faster-allreduce-with-nvswitch-and-tensorrt-llm-multishot/feed/ 0 3278 人人超碰97caoporen国产