GB200
PulseAugur coverage of GB200 — every cluster mentioning GB200 across labs, papers, and developer communities, ranked by signal.
2 天有情绪数据
-
PiD decoder speeds up high-res image generation with pixel diffusion
Researchers have developed PiD, a novel pixel diffusion decoder that significantly enhances image generation quality and speed. This new method reformulates latent decoding as a conditional pixel diffusion process, allo…
-
New metric OFU tracks GPU efficiency for AI workloads
Researchers have developed a new metric called Overall FLOP Utilization (OFU) to measure GPU efficiency for AI workloads. OFU is derived from on-chip performance counters and does not require application instrumentation…
-
Nvidia's GB300 GPU shows 2.7x faster inference than GB200
Nvidia's GB300 ultra NVL72 has demonstrated a 2.7x speed advantage over the GB200 NVL72 in inference tasks using the vLLM project's engine. This performance leap exceeds theoretical expectations based on the GB300's spe…