RedHatAI/Inkling-FP8-dynamic
Quantization vs thinkingmachines/Inkling. RedHatAI/Inkling-FP8-dynamic is a quantized version of the other (F8_E4M3/BF16).
Quantization vs thinkingmachines/Inkling. RedHatAI/Inkling-FP8-dynamic is a quantized version of the other (F8_E4M3/BF16).