From 0160f6b3efdd9e7fd018ccafa95518a69466a28f Mon Sep 17 00:00:00 2001 From: Disty0 Date: Tue, 24 Feb 2026 20:08:41 +0300 Subject: [PATCH] add sdnq variants of pytorch native fp formats too --- modules/sdnq/common.py | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/modules/sdnq/common.py b/modules/sdnq/common.py index 055a51b8c..8edc3bcf4 100644 --- a/modules/sdnq/common.py +++ b/modules/sdnq/common.py @@ -38,16 +38,16 @@ dtype_dict = { "float8_e4m3fn": {"min": -448.0, "max": 448.0, "num_bits": 8, "sign": 1, "exponent": 4, "mantissa": 3, "target_dtype": torch.float8_e4m3fn, "torch_dtype": torch.float8_e4m3fn, "storage_dtype": torch.float8_e4m3fn, "is_unsigned": False, "is_integer": False, "is_packed": False}, "float8_e5m2": {"min": -57344.0, "max": 57344.0, "num_bits": 8, "sign": 1, "exponent": 5, "mantissa": 2, "target_dtype": torch.float8_e5m2, "torch_dtype": torch.float8_e5m2, "storage_dtype": torch.float8_e5m2, "is_unsigned": False, "is_integer": False, "is_packed": False}, ### Custom Floats - "float16_e1m14fn": {"min": -3.9998779296875, "max": 3.9998779296875, "num_bits": 16, "sign": 1, "exponent": 1, "mantissa": 14, "min_normal": 1.00006103515625, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, - "float16_e2m13fn": {"min": -7.99951171875, "max": 7.99951171875, "num_bits": 16, "sign": 1, "exponent": 2, "mantissa": 13, "min_normal": 0.50006103515625, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, - "float16_e3m12fn": {"min": -31.99609375, "max": 31.99609375, "num_bits": 16, "sign": 1, "exponent": 3, "mantissa": 12, "min_normal": 0.125030517578125, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, - "float16_e4m11fn": {"min": -511.875, "max": 511.875, "num_bits": 16, "sign": 1, "exponent": 4, "mantissa": 11, "min_normal": 0.007816314697265625, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, - # float16_e5m10 is native in PyTorch + "float16_e1m14fn": {"min": -3.9998779296875, "max": 3.9998779296875, "num_bits": 16, "sign": 1, "exponent": 1, "mantissa": 14, "min_normal": 1.00006103515625, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, + "float16_e2m13fn": {"min": -7.99951171875, "max": 7.99951171875, "num_bits": 16, "sign": 1, "exponent": 2, "mantissa": 13, "min_normal": 0.50006103515625, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, + "float16_e3m12fn": {"min": -31.99609375, "max": 31.99609375, "num_bits": 16, "sign": 1, "exponent": 3, "mantissa": 12, "min_normal": 0.125030517578125, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, + "float16_e4m11fn": {"min": -511.875, "max": 511.875, "num_bits": 16, "sign": 1, "exponent": 4, "mantissa": 11, "min_normal": 0.007816314697265625, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, + "float16_e5m10fn": {"min": -131008.0, "max": 131008.0, "num_bits": 16, "sign": 1, "exponent": 5, "mantissa": 10, "min_normal": 3.0547380447387695e-05, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": False, "is_integer": False, "is_packed": True}, "float8_e1m6fn": {"min": -3.96875, "max": 3.96875, "num_bits": 8, "sign": 1, "exponent": 1, "mantissa": 6, "min_normal": 1.015625, "target_dtype": "fp8", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, "float8_e2m5fn": {"min": -7.875, "max": 7.875, "num_bits": 8, "sign": 1, "exponent": 2, "mantissa": 5, "min_normal": 0.515625, "target_dtype": "fp8", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, "float8_e3m4fn": {"min": -31.0, "max": 31.0, "num_bits": 8, "sign": 1, "exponent": 3, "mantissa": 4, "min_normal": 0.1328125, "target_dtype": "fp8", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, - # float8_e4m3fn is native in PyTorch - # float8_e5m2fn is native in PyTorch + "float8_e4m3fn_sdnq": {"min": -480.0, "max": 480.0, "num_bits": 8, "sign": 1, "exponent": 4, "mantissa": 3, "min_normal": 0.0087890625, "target_dtype": "fp8", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, + "float8_e5m2fn": {"min": -114688.0, "max": 114688.0, "num_bits": 8, "sign": 1, "exponent": 5, "mantissa": 2, "min_normal": 3.814697265625e-05, "target_dtype": "fp8", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, "float7_e1m5fn": {"min": -3.9375, "max": 3.9375, "num_bits": 7, "sign": 1, "exponent": 1, "mantissa": 5, "min_normal": 1.03125, "target_dtype": "fp7", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, "float7_e2m4fn": {"min": -7.75, "max": 7.75, "num_bits": 7, "sign": 1, "exponent": 2, "mantissa": 4, "min_normal": 0.53125, "target_dtype": "fp7", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, "float7_e3m3fn": {"min": -30.0, "max": 30.0, "num_bits": 7, "sign": 1, "exponent": 3, "mantissa": 3, "min_normal": 0.140625, "target_dtype": "fp7", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, @@ -74,11 +74,11 @@ dtype_dict = { # "float2_e1m0fn": {"min": -2.0, "max": 2.0, "num_bits": 2, "sign": 1, "exponent": 1, "mantissa": 0, "min_normal": 2.0, "target_dtype": "fp2", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": False, "is_integer": False, "is_packed": True}, ### Custom Usigned Floats - "float16_e1m15fnu": {"min": 0, "max": 3.99993896484375, "num_bits": 16, "sign": 0, "exponent": 1, "mantissa": 15, "min_normal": 1.000030517578125, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, - "float16_e2m14fnu": {"min": 0, "max": 7.999755859375, "num_bits": 16, "sign": 0, "exponent": 2, "mantissa": 14, "min_normal": 0.500030517578125, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, - "float16_e3m13fnu": {"min": 0, "max": 31.998046875, "num_bits": 16, "sign": 0, "exponent": 3, "mantissa": 13, "min_normal": 0.1250152587890625, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, - "float16_e4m12fnu": {"min": 0, "max": 511.9375, "num_bits": 16, "sign": 0, "exponent": 4, "mantissa": 12, "min_normal": 0.007814407348632812, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, - "float16_e5m11fnu": {"min": 0, "max": 131040.0, "num_bits": 16, "sign": 0, "exponent": 5, "mantissa": 11, "min_normal": 3.053247928619385e-05, "target_dtype": torch.float16, "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, + "float16_e1m15fnu": {"min": 0, "max": 3.99993896484375, "num_bits": 16, "sign": 0, "exponent": 1, "mantissa": 15, "min_normal": 1.000030517578125, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, + "float16_e2m14fnu": {"min": 0, "max": 7.999755859375, "num_bits": 16, "sign": 0, "exponent": 2, "mantissa": 14, "min_normal": 0.500030517578125, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, + "float16_e3m13fnu": {"min": 0, "max": 31.998046875, "num_bits": 16, "sign": 0, "exponent": 3, "mantissa": 13, "min_normal": 0.1250152587890625, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, + "float16_e4m12fnu": {"min": 0, "max": 511.9375, "num_bits": 16, "sign": 0, "exponent": 4, "mantissa": 12, "min_normal": 0.007814407348632812, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, + "float16_e5m11fnu": {"min": 0, "max": 131040.0, "num_bits": 16, "sign": 0, "exponent": 5, "mantissa": 11, "min_normal": 3.053247928619385e-05, "target_dtype": "fp16", "torch_dtype": torch.float32, "storage_dtype": torch.uint16, "is_unsigned": True, "is_integer": False, "is_packed": True}, # "float8_e1m7fnu": {"min": 0, "max": 3.984375, "num_bits": 8, "sign": 0, "exponent": 1, "mantissa": 7, "min_normal": 1.0078125, "target_dtype": "fp8", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": True, "is_integer": False, "is_packed": True}, "float8_e2m6fnu": {"min": 0, "max": 7.9375, "num_bits": 8, "sign": 0, "exponent": 2, "mantissa": 6, "min_normal": 0.5078125, "target_dtype": "fp8", "torch_dtype": torch.float32, "storage_dtype": torch.uint8, "is_unsigned": True, "is_integer": False, "is_packed": True}, @@ -176,11 +176,11 @@ weights_dtype_order = [ "uint6", "float6_e1m5fnu", "float6_e2m4fnu", "float6_e3m3fnu", "float6_e4m2fnu", "float6_e5m1fnu", "int7", "float7_e1m5fn", "float7_e2m4fn", "float7_e3m3fn", "float7_e4m2fn", "float7_e5m1fn", "uint7", "float7_e1m6fnu", "float7_e2m5fnu", "float7_e3m4fnu", "float7_e4m3fnu", "float7_e5m2fnu", - "int8", "float8_e4m3fn", "float8_e5m2", "float8_e1m6fn", "float8_e2m5fn", "float8_e3m4fn", + "int8", "float8_e4m3fn", "float8_e5m2", "float8_e1m6fn", "float8_e2m5fn", "float8_e3m4fn", "float8_e4m3fn_sdnq", "float8_e5m2fn", "uint8", "float8_e1m7fnu", "float8_e2m6fnu", "float8_e3m5fnu", "float8_e4m4fnu", "float8_e5m3fnu", ] weights_dtype_order_fp32 = weights_dtype_order + [ - "int16", "float16", "float16_e1m14fn", "float16_e2m13fn", "float16_e3m12fn", "float16_e4m11fn", + "int16", "float16", "float16_e1m14fn", "float16_e2m13fn", "float16_e3m12fn", "float16_e4m11fn", "float16_e5m10fn", "uint16", "float16_e1m15fnu", "float16_e2m14fnu", "float16_e3m13fnu", "float16_e4m12fnu", "float16_e5m11fnu", ]