Skip to content

Assert quant_min/quant_max in embedding4bit #28590

Assert quant_min/quant_max in embedding4bit

Assert quant_min/quant_max in embedding4bit #28590

test-llama-runner-linux (fp32, xnnpack+custom+quantize_kv)  /  linux-job

succeeded Dec 20, 2024 in 10m 9s