正在加载视频...
视频加载失败
MI355 disaggregated serving is competitive to B200 disaggregated serving for FP8 but when composability all the optimizations that frontier labs use together like wide expert parallelism+disagg+FP4+kvcache offloading AMD is still jestermaxxing & lackluster. King Anush Elangovan needs to focus on composability of inference optimizations for ROCm stack in order... show more
22,416 次观看 • 4 个月前 •via X (Twitter)
0 条评论
暂无评论
原始帖子的评论将显示在这里
