新浪网5 天
AMD跑DeepSeek性能超H200！128并发Token间延迟不超50ms，吞吐量达H200五倍
在AMD的MI300X上跑FP8满血R1，性能全面超越了英伟达H200—— 相同延迟下吞吐量最高可达H200的5倍，相同并发下则比H200高出75%。 这个结果，一方面归功 ...
CRN4 个月
Nvidia Reveals 4-GPU GB200 NVL4 Superchip, Releases H200 NVL Module
The NVL4 module contains Nvidia’s H200 GPU that launched earlier this year in the SXM form factor for Nvidia’s DGX system as well as HGX systems from server vendors. The H200 is the successor ...
来自MSN4 个月
英伟达发布新AI硬件：H200 NVL PCIe GPU 和 GB200 NVL4 超级芯片
最高 TDP 功耗从 H200 SXM 的 700W 降至 600W，各算力也均有一定下降（IT之家注：如 INT8 Tensor Core 算力下滑约 15.6% ），不过 HBM 内存容量和带宽是与 H200 SXM ...
CRN1 年
Nvidia’s H200 GPU To One-Up H100 With 141GB Of HBM3e As Memory Race Heats Up
The H200 features 141GB of HBM3e and a 4.8 TB/s memory bandwidth, a substantial step up from Nvidia’s flagship H100 data center GPU. ‘The integration of faster and more extensive memory will ...
来自MSN4 个月
Nvidia introduces a new merged CPU and GPU AI processor — GB200 Grace Blackwell NVL4 ...
Performance is slightly worse than Nvidia's outgoing H200 in the SXM form factor. The H200 NVL is rated at 30 TFLOPS of FP64 and 60 TFLOPS of FP32. Tensor core performance is rated at 60 TFLOPS of ...