9 Commits

Author	SHA1	Message	Date
Yu Li	5ba2d28b7f	add block-wise scaled int8 quantization based on QuantizedLayout mechanism ... add more tests by comparing with manual torch implementation add perf benchmarks fix errors caused by merging default no output quant fix unittest	2025-12-10 12:23:05 -06:00
comfyanonymous	73e3a9e676	Clamp output when rounding weight to prevent Nan.	2024-10-19 19:07:10 -04:00
comfyanonymous	7d2467e830	Some minor cleanups.	2024-10-05 13:22:39 -04:00
comfyanonymous	00a5d08103	Lower fp8 lora memory usage.	2024-09-03 01:25:05 -04:00
comfyanonymous	2ca8f6e23d	Make the stochastic fp8 rounding reproducible.	2024-08-26 15:12:06 -04:00
comfyanonymous	7985ff88b9	Use less memory in float8 lora patching by doing calculations in fp16.	2024-08-26 14:45:58 -04:00
comfyanonymous	4506ddc86a	Better subnormal fp8 stochastic rounding. Thanks Ashen.	2024-08-19 13:38:03 -04:00
comfyanonymous	22ec02afc0	Handle subnormal numbers in float8 rounding.	2024-08-19 05:51:08 -04:00
comfyanonymous	bb222ceddb	Fix loras having a weak effect when applied on fp8.	2024-08-17 15:20:17 -04:00