Tracked topic
…This eases the deployment of agentic calibration workflows directly in local lab environments. For the first time, the model is also available in an NVFP4 -quantized version, enabling deployment on a single…
…BF16 and NVFP4 The model is available today on Hugging Face with BF16 checkpoints, and an NVFP4 quantized checkpoint for DiffusionGemma is also available using NVIDIA Model Optimizer . Enterprise deployments with NVIDIA…
…NVFP4 Accelerates LLM Training Key to the outstanding results this round was performing calculations using NVFP4 precision — a first in the history of MLPerf Training. One way to increase compute performance is…
…NVIDIA continues to push low-precision training innovation across different model architectures, most recently using NVFP4 to pretrain the massive 550-billion-parameter NVIDIA Nemotron 3 Ultra model. NVIDIA GB300 NVL72 Delivered…
Here's a brand new Blackwell-native, prefill-optimized 4-bit quant that runs 50% faster on compatible hardware than a Q4 quant of the same memory footprint. And it runs 4-7% faster than other NVFP4 quants as benchmarked …
These are single stream numbers Following on from my previous post about v100s (here) and inspired by this comment (here) I decided to work on kernels that allow for an extremely fast path for Nvfp4 weights on sm70 and a…
Four Tesla V100s from 2017 matched my RTX 5090 on single-request Qwen 3.8 decode. Repo: https://github.com/dnv2003/v100-skinny https://i.redd.it/5ws2ak3uqckh1.gif The 5090 was not being held back. It ran NInfer, a specia…
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…
Poolside have updated the FP8 and NVFP4 checkpoints for Laguna S 2.1, increasing the default context size to 1 million, and updating the configs. Here's hoping they fixed the looping issue, this model has been great in m…
…CoreWeave has deployed Kimi K2.6 on NVIDIA GB300 NVL72, combining NVFP4 quantization and EAGLE3 speculative decoding to maximize inference performance. Perplexity runs Qwen3 235B and post-trained Qwen3.5-397B-A17B…
…Swipe to scroll horizontally Nvidia Rubin GPU Row 0 - Cell 1 NVFP4 Inference 50 PFLOPS (with sparsity) NVFP4 Training 35 PFLOPS FP8/FP6 Training 17.5 PFLOPS INT8 250 TOPS FP16/BF16…
DeepSeek V4 is out , bringing major optimizations, including up to 1.6T model sizes, and NVIDIA is ready with Day-0 support on Blackwell GPUs using NVFP4. NVIDIA Blackwell NVFP4 Architecture Delivers…
…The chip itself is designed purely for AI-intensive workloads, offering 50 FLOPs of NVFP4 Inference, 35 PFLOPs of NVFP4 Training performance, a 5x and 3.5x increase over Blackwell, respectively. The…
…The chip itself is designed purely for AI-intensive workloads, offering 50 FLOPs of NVFP4 Inference, 35 PFLOPs of NVFP4 Training performance, a 5x and 3.5x increase over Blackwell, respectively. The…
…양자화 Nemotron 3.5 Lightning은 BF16과 함께 NVFP4 체크포인트를 제공하며, NVIDIA Blackwell, NVIDIA Hopper, NVIDIA Ampere GPU 전반에서 Nemotron 3 Ultra를 구동하는 동일한 특화 NVFP4 커널을 사용합니다. 동일한 파일이 데이터 센터에서와 마찬가지로…