Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-20 01:31:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

SDNQ update RDNA2 detection

Browse Source
This commit is contained in:
Disty0
2026-04-16 08:34:17 +03:00
parent 0541843a86
commit eba2c3a8a3
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sdnq/common.py
+8 -3
View File
@@ -328,13 +328,18 @@ weights_dtype_order = [
"uint16", "float16_e1m15fnu", "float16_e2m14fnu", "float16_e3m13fnu", "float16_e4m12fnu", "float16_e5m11fnu",
]
is_rdna2 = bool(devices.backend == "rocm" and devices.get_hip_agent().gfx_version < 0x1100)
use_torch_compile = shared.opts.sdnq_dequantize_compile # this setting requires a full restart of the webui to apply
def check_torch_compile(): # dynamo can be disabled after startup
return use_torch_compile and not torch._dynamo.config.disable # pylint: disable=protected-access
if devices.backend == "rocm":
gfx_version = devices.get_hip_agent().gfx_version
is_rdna2_and_older = bool(gfx_version < 0x940 or (gfx_version < 0x1100 and gfx_version >= 0x1000))
else:
is_rdna2_and_older = False
if os.environ.get("SDNQ_ALLOW_FP8_MM", None) is None:
if devices.backend == "cuda":
is_fp8_mm_supported = bool(torch.cuda.get_device_capability(devices.device) >= (8,9))
@@ -353,12 +358,12 @@ else:
use_tensorwise_fp8_matmul = 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_mm = bool(is_rdna2 or devices.backend in {"ipex", "mps", "cpu", "openvino", "zluda"})
use_contiguous_mm = bool(is_rdna2_and_older or devices.backend in {"ipex", "mps", "cpu", "openvino", "zluda"})
else:
use_contiguous_mm = bool(os.environ.get("SDNQ_USE_CONTIGUOUS_MM", "0").lower() not in {"0", "false", "no"})
if os.environ.get("SDNQ_USE_TRITON_MM", None) is None:
use_triton_mm = bool(is_rdna2 or devices.backend == "zluda")
use_triton_mm = bool(is_rdna2_and_older or devices.backend == "zluda")
else:
use_triton_mm = bool(os.environ.get("SDNQ_USE_TRITON_MM", "0").lower() not in {"0", "false", "no"})