IPEX fixes

html/locale_en.json

@@ -383,6 +383,7 @@
   {"id":"","label":"Model compile suppress errors","localized":"","hint":""},
   {"id":"","label":"Disable Torch memory garbage collection","localized":"","hint":"Disable Torch memory garbage collection on each generation. CG will still run before & after model load as well when low GPU memory threshold is reached."},
   {"id":"","label":"Directory for temporary images; leave empty for default","localized":"","hint":""},
+  {"id":"","label":"Enable IPEX Optimize for Intel GPUs","localized":"","hint":""},
   {"id":"","label":"Cleanup non-default temporary directory when starting webui","localized":"","hint":""},
   {"id":"","label":"Path to directory with stable diffusion checkpoints","localized":"","hint":""},
   {"id":"","label":"Path to directory with stable diffusion diffusers","localized":"","hint":""},

html/locale_ko.json

@@ -382,6 +382,7 @@
   {"id":"","label":"Model compile verbose mode","localized":"","hint":""},
   {"id":"","label":"Model compile suppress errors","localized":"모델 컴파일 시 오류 억제","hint":""},
   {"id":"","label":"Disable Torch memory garbage collection","localized":"Torch 메모리 정리 비활성화","hint":"이미지 생성 시 메모리 정리를 하지 않는다. CG will still run before & after model load as well when low GPU memory threshold is reached."},
+  {"id":"","label":"Enable IPEX Optimize for Intel GPUs","localized":"","hint":""},
   {"id":"","label":"Directory for temporary images; leave empty for default","localized":"임시 이미지 저장 위치 (비워 놓으면 기본값)","hint":""},
   {"id":"","label":"Cleanup non-default temporary directory when starting webui","localized":"임시 위치가 기본값이 아닌 경우 WebUI 시작 시 비우기","hint":""},
   {"id":"","label":"Path to directory with stable diffusion checkpoints","localized":"체크포인트 위치","hint":""},

installer.py

@@ -185,8 +185,6 @@ def install(package, friendly: str = None, ignore: bool = False):
     if args.reinstall or args.upgrade:
         global quick_allowed # pylint: disable=global-statement
         quick_allowed = False
-    if args.use_ipex and package == "pytorch_lightning==1.9.4":
-        package = "pytorch_lightning==1.8.6"
     if args.reinstall or not installed(package, friendly):
         pip(f"install --upgrade {package}", ignore=ignore)
 

modules/ipex_specific/__init__.py

@@ -21,39 +21,72 @@ def return_null_context(*args, **kwargs):
     return contextlib.nullcontext()
 
 def ipex_init():
-    #Fix functions with ipex
-    torch.cuda.is_available = torch.xpu.is_available
+    #Replace cuda with xpu:
+    torch.cuda.current_device = torch.xpu.current_device
+    torch.cuda.current_stream = torch.xpu.current_stream
     torch.cuda.device = torch.xpu.device
     torch.cuda.device_count = torch.xpu.device_count
-    torch.cuda.current_device = torch.xpu.current_device
+    torch.cuda.device_of = torch.xpu.device_of
+    torch.cuda.getDeviceIdListForCard = torch.xpu.getDeviceIdListForCard
     torch.cuda.get_device_name = torch.xpu.get_device_name
     torch.cuda.get_device_properties = torch.xpu.get_device_properties
-    torch._utils._get_available_device_type = lambda: "xpu" # pylint: disable=protected-access
+    torch.cuda.init = torch.xpu.init
+    torch.cuda.is_available = torch.xpu.is_available
+    torch.cuda.is_initialized = torch.xpu.is_initialized
     torch.cuda.set_device = torch.xpu.set_device
+    torch.cuda.stream = torch.xpu.stream
     torch.cuda.synchronize = torch.xpu.synchronize
-    torch.backends.cuda.sdp_kernel = return_null_context
+    torch.cuda.Event = torch.xpu.Event
     torch.Tensor.cuda = torch.Tensor.xpu
-    torch.nn.DataParallel = DummyDataParallel
+    torch.Tensor.is_cuda = torch.Tensor.is_xpu
+    torch.cuda.Stream = torch.xpu.Stream
 
     #Memory:
-    torch.xpu.empty_cache = torch.xpu.empty_cache if "WSL2" not in os.popen("uname -a").read() else lambda: None
     torch.cuda.empty_cache = torch.xpu.empty_cache
-    torch.cuda.ipc_collect = lambda: None
     torch.cuda.memory_stats = torch.xpu.memory_stats
-    torch.cuda.mem_get_info = lambda device=None: [(torch.xpu.get_device_properties(device).total_memory - torch.xpu.memory_allocated(device)), torch.xpu.get_device_properties(device).total_memory]
+    torch.cuda.memory_summary = torch.xpu.memory_summary
+    torch.cuda.memory_snapshot = torch.xpu.memory_snapshot
     torch.cuda.memory_allocated = torch.xpu.memory_allocated
     torch.cuda.max_memory_allocated = torch.xpu.max_memory_allocated
+    torch.cuda.memory_reserved = torch.xpu.memory_reserved
+    torch.cuda.max_memory_reserved = torch.xpu.max_memory_reserved
     torch.cuda.reset_peak_memory_stats = torch.xpu.reset_peak_memory_stats
-    torch.cuda.utilization = lambda: 0
+    torch.cuda.memory_stats_as_nested_dict = torch.xpu.memory_stats_as_nested_dict
+    torch.cuda.reset_accumulated_memory_stats = torch.xpu.reset_accumulated_memory_stats
+
+    #RNG:
+    torch.cuda.get_rng_state = torch.xpu.get_rng_state
+    torch.cuda.get_rng_state_all = torch.xpu.get_rng_state_all
+    torch.cuda.set_rng_state = torch.xpu.set_rng_state
+    torch.cuda.set_rng_state_all = torch.xpu.set_rng_state_all
+    torch.cuda.manual_seed = torch.xpu.manual_seed
+    torch.cuda.manual_seed_all = torch.xpu.manual_seed_all
+    torch.cuda.seed = torch.xpu.seed
+    torch.cuda.seed_all = torch.xpu.seed_all
+    torch.cuda.initial_seed = torch.xpu.initial_seed
 
     #Training:
-    torch.cuda.get_rng_state_all = torch.xpu.get_rng_state_all
-    torch.cuda.set_rng_state_all = torch.xpu.set_rng_state_all
     try:
         torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
     except Exception:
         torch.cuda.amp.GradScaler = ipex.cpu.autocast._grad_scaler.GradScaler
 
+    #C
+    torch._C._cuda_getCurrentRawStream = ipex._C._getCurrentStream
+    ipex._C._DeviceProperties.major = 2023
+    ipex._C._DeviceProperties.minor = 2
+
+    #Fix functions with ipex:
+    torch.cuda.mem_get_info = lambda device=None: [(torch.xpu.get_device_properties(device).total_memory - torch.xpu.memory_allocated(device)), torch.xpu.get_device_properties(device).total_memory]
+    torch._utils._get_available_device_type = lambda: "xpu" # pylint: disable=protected-access
+    torch.xpu.empty_cache = torch.xpu.empty_cache if "WSL2" not in os.popen("uname -a").read() else lambda: None
+    torch.cuda.get_device_properties.major = 2023
+    torch.cuda.get_device_properties.minor = 2
+    torch.backends.cuda.sdp_kernel = return_null_context
+    torch.nn.DataParallel = DummyDataParallel
+    torch.cuda.ipc_collect = lambda: None
+    torch.cuda.utilization = lambda: 0
+
     #Libraries that blindly uses cuda:
     #Adetailer:
     CondFunc('torch.Tensor.to',

webui.sh

@@ -96,10 +96,6 @@ if [[ ! -z "${ACCELERATE}" ]] && [ ${ACCELERATE}="True" ] && [ -x "$(command -v
 then
     echo "Launching accelerate launch.py..."
     exec accelerate launch --num_cpu_threads_per_process=6 launch.py "$@"
-elif [[ -z "${first_launch}" ]] && [ -x "$(command -v ipexrun)" ] && [ -x "$(command -v numactl)" ] && [ -x "$(command -v sycl-ls)" ]
-then
-    echo "Launching ipexrun launch.py..."
-    exec ipexrun launch.py "$@"
 else
     echo "Launching launch.py..."
     exec "${python_cmd}" launch.py "$@"