Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 01:04:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

cleanup

Browse Source
This commit is contained in:
Dity0
2026-08-04 11:18:54 +03:00
parent 89d2bef078
commit b76ec32ac0
1 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sdnq/kernel_wrappers.py
+9 -9
View File
@@ -49,15 +49,6 @@ if os.environ.get("SDNQ_USE_TENSORWISE_FP8_MM", None) is None:
else:
use_tensorwise_fp8_matmul = bool(os.environ.get("SDNQ_USE_TENSORWISE_FP8_MM", "0").lower() not in {"0", "false", "no"})
if os.environ.get("SDNQ_USE_CONTIGUOUS_MM", None) is None:
use_contiguous_int8_mm = bool(is_rdna2_and_older or devices.backend in {"ipex", "xpu", "cpu", "mps", "openvino", "zluda"})
use_contiguous_fp16_mm = bool(use_contiguous_int8_mm or devices.backend == "rocm")
use_contiguous_fp8_mm = use_contiguous_fp16_mm and (is_fp8_mm_supported or use_triton_mm)
else:
use_contiguous_int8_mm = bool(os.environ.get("SDNQ_USE_CONTIGUOUS_MM", "0").lower() not in {"0", "false", "no"})
use_contiguous_fp16_mm = use_contiguous_int8_mm
use_contiguous_fp8_mm = use_contiguous_fp16_mm and (is_fp8_mm_supported or use_triton_mm)
use_openvino_mm = bool(os.environ.get("SDNQ_USE_OPENVINO_MM", "1").lower() not in {"0", "false", "no"})
use_triton_scaled_mm = bool(use_triton_mm and os.environ.get("SDNQ_USE_TRITON_SCALED_MM", "1").lower() not in {"0", "false", "no"})
@@ -104,6 +95,15 @@ if os.environ.get("SDNQ_INCLUDE_MM_KERNEL_IN_COMPILE", None) is None:
else:
include_mm_kernel_in_compile = bool(os.environ.get("SDNQ_INCLUDE_MM_KERNEL_IN_COMPILE", "0").lower() not in {"0", "false", "no"})
if os.environ.get("SDNQ_USE_CONTIGUOUS_MM", None) is None:
use_contiguous_int8_mm = bool(is_rdna2_and_older or devices.backend in {"ipex", "xpu", "cpu", "mps", "openvino", "zluda"})
use_contiguous_fp16_mm = bool(use_contiguous_int8_mm or devices.backend == "rocm")
use_contiguous_fp8_mm = use_contiguous_fp16_mm and (is_fp8_mm_supported and use_triton_mm)
else:
use_contiguous_int8_mm = bool(os.environ.get("SDNQ_USE_CONTIGUOUS_MM", "0").lower() not in {"0", "false", "no"})
use_contiguous_fp16_mm = use_contiguous_int8_mm
use_contiguous_fp8_mm = use_contiguous_fp16_mm and (is_fp8_mm_supported and use_triton_mm)
def int_mm_torch(a: torch.Tensor, b: torch.Tensor, out_dtype: torch.dtype = torch.int32) -> torch.FloatTensor:
return torch._int_mm(a,b).to(dtype=out_dtype)