Tracked topic
…エージェント型推論向けのオープン ハイブリッド Mamba-Transformer MoE Nemotron 3 Super は、高容量の推論モデルにおける典型的な効率と精度のトレードオフを軽減するアーキテクチャ革新を導入しています。 3 MIN READ 2026 年 2 月 6 日 NVFP4 が AI のトレーニングと推論を加速する 3 つの方法 NVIDIA による徹底的な共同設計によって、モデルのトレーニングと推論の両方において、優れた精度で大幅なパフォーマンスの向上が達成が見込めるようになりました。 2 MIN READ…
…重要なポイントが 1 つあるとすれば、適切な量子化の精度を使用することです。 NVFP4、INT4、W4A16 などのフォーマットは、多くの LLM ワークロードで高い精度を維持しながら、メモリとストレージの要件を大幅に削減します。 実際のユース ケース: Reachy Mini Jetson Mini Assistant これらのメモリ最適化の効果を示すために、Jetson Orin Nano 上で実行されるオンデバイス対話型 AI ロボットである Reachy Mini Jetson Assistant を考えてみましょう。これは…
…a single GPU; its distilled variant can be deployed on a single RTX 5090 with NVFP4 quantization to denoise a 60s 720p clip in 34s. On our one-minute world-model benchmark…
…NVIDIA GB300 NVL72 demonstrates up to 20x higher agentic coding performance. The NVIDIA Vera Rubin platform is expected to extend these gains by leveraging 50 PFLOPs of NVFP4 compute and leveraging the…
Safetensors, llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved: https://huggingface.co/llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved GGUFs, llmfan46/Qwen3.5-35B-A3B-uncensored-here…
Build is done. 16 DGX Sparks on the fabric, all hitting line rate. Setup was time consuming but honestly smoother than I expected. Each Spark runs Nvidia’s flavor of Ubuntu out of the box with mostly everything pre insta…
Added a 16x Spark Cluster to my homelab over the last few days. Curious if this is the largest Spark cluster anyone has built. About 2 years ago I had renovated my basement and built a personal lab/datacenter into my off…
Added a 16x Spark Cluster to my homelab over the last few days. Curious if this is the largest Spark cluster anyone has built. About 2 years ago I had renovated my basement and built a personal lab/datacenter into my off…
…Baseten used the low-precision NVFP4 data format, the NVIDIA TensorRT-LLM library — an open source C++/Python framework for optimizing large language model inference on NVIDIA GPUs that includes tensor parallelism…
…Cosmos 3 NIM은 BF16, FP8, NVFP4 양자화 체크포인트 선택을 지원합니다. NVFP4 양자화는 모델의 수치 정밀도를 BF16에서 4비트 부동소수점으로 낮춰 최대 2배의 추론 속도 향상을 달성합니다. vLLM: 연속 배칭(continuous batching), 페이지드 어텐션…
…That was combined with the powerful compute capabilities of Blackwell, along with NVFP4 weight quantization, for an additional 2x speedup, with an even bigger performance gain of 2.8x seen at higher…
…There's also support for Nvidia's NVFP4 format, which can maintain model accuracy while also reducing the memory bandwidth. High-spec only To end users who work with LLMs…
…Native NVFP4 pretraining optimized for NVIDIA Blackwell, significantly cutting memory requirements and speeding up inference by 4x on NVIDIA B200 compared to FP8 on NVIDIA H100, while maintaining accuracy. Multi-environment reinforcement…
…The NVIDIA Blackwell architecture powering DGX Spark includes the NVFP4 data format, which enables AI models to be compressed by up to 70% and boosts performance without losing intelligence. NVIDIA’s collaborations…