[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
OnlyCalls @0xOnlyCalls on x 4881 followers
Created: 2025-07-18 15:03:57 UTC
Apple device clusters have more VRAM but fewer FLOPS compared to NVIDIA GPUs.
KPOP, a new DL optimizer, shows better efficiency per FLOP than Adam while using more memory.
Apple's hardware could become viable for large-scale LLM training, diversifying compute options beyond ...
XX engagements
Related Topics llm kpop $nvda stocks technology