Add Paged/ adam8bit/lion8bit for Sdxl bitsandbytes 0.39.1 cuda118 on windows (#623)

* ADD libbitsandbytes.dll for 0.38.1

* Delete libbitsandbytes_cuda116.dll

* Delete cextension.py

* add main.py

* Update requirements.txt for bitsandbytes 0.38.1

* Update README.md for bitsandbytes-windows

* Update README-ja.md  for bitsandbytes 0.38.1

* Update main.py for return cuda118

* Update train_util.py for lion8bit

* Update train_README-ja.md for lion8bit

* Update train_util.py for add DAdaptAdan and DAdaptSGD

* Update train_util.py for DAdaptadam

* Update train_network.py for dadapt

* Update train_README-ja.md for DAdapt

* Update train_util.py for DAdapt

* Update train_network.py for DAdaptAdaGrad

* Update train_db.py for DAdapt

* Update fine_tune.py for DAdapt

* Update train_textual_inversion.py for DAdapt

* Update train_textual_inversion_XTI.py for DAdapt

* Revert "Merge branch 'qinglong' into main"

This reverts commit b65c023083, reversing
changes made to f6fda20caf.

* Revert "Update requirements.txt for bitsandbytes 0.38.1"

This reverts commit 83abc60dfa.

* Revert "Delete cextension.py"

This reverts commit 3ba4dfe046.

* Revert "Update README.md for bitsandbytes-windows"

This reverts commit 4642c52086.

* Revert "Update README-ja.md  for bitsandbytes 0.38.1"

This reverts commit fa6d7485ac.

* Update train_util.py for DAdaptLion

* Update train_README-zh.md for dadaptlion

* Update train_README-ja.md for DAdaptLion

* add DAdatpt V3

* Alignment

* Update train_util.py for experimental

* Update train_util.py V3

* Update train_util.py

* Update requirements.txt

* Update train_README-zh.md

* Update train_README-ja.md

* Update train_util.py fix

* Update train_util.py

* support Prodigy

* add lower

* Update main.py

* support PagedAdamW8bit/PagedLion8bit

* Update requirements.txt

* update for PageAdamW8bit and PagedLion8bit

* Revert

* revert main

* Update train_util.py

* update for bitsandbytes 0.39.1

* Update requirements.txt

* vram leak fix

---------

Co-authored-by: Pam <pamhome21@gmail.com>

bitsandbytes_windows/main.py

@@ -4,7 +4,7 @@ extract factors the build is dependent on:
     [ ] TODO: Q - What if we have multiple GPUs of different makes?
 - CUDA version
 - Software:
-    - CPU-only: only CPU quantization functions (no optimizer, no matrix multiple)
+    - CPU-only: only CPU quantization functions (no optimizer, no matrix multipl)
     - CuBLAS-LT: full-build 8-bit optimizer
     - no CuBLAS-LT: no 8-bit matrix multiplication (`nomatmul`)
 
@@ -16,35 +16,367 @@ evaluation:
         - based on that set the default path
 """
 
-import ctypes
+import ctypes as ct
+import os
+import errno
+import torch
+import platform
+from warnings import warn
+from itertools import product
 
-from .paths import determine_cuda_runtime_lib_path
+from pathlib import Path
+from typing import Set, Union
+from .env_vars import get_potentially_lib_path_containing_env_vars
+
+# these are the most common libs names
+# libcudart.so is missing by default for a conda install with PyTorch 2.0 and instead
+# we have libcudart.so.11.0 which causes a lot of errors before
+# not sure if libcudart.so.12.0 exists in pytorch installs, but it does not hurt
+CUDA_RUNTIME_LIBS: list = ["libcudart.so", 'libcudart.so.11.0', 'libcudart.so.12.0']
+
+# this is a order list of backup paths to search CUDA in, if it cannot be found in the main environmental paths
+backup_paths = []
+
+
+IS_WINDOWS_PLATFORM: bool = (platform.system()=="Windows")
+PATH_COLLECTION_SEPARATOR: str = ":" if not IS_WINDOWS_PLATFORM else ";"
+CUDA_RUNTIME_LIBS: list = ["libcudart.so", 'libcudart.so.11.0', 'libcudart.so.12.0'] if not IS_WINDOWS_PLATFORM else ["cudart64_110.dll", "cudart64_120.dll", "cudart64_12.dll"]
+backup_paths.append('$CONDA_PREFIX/lib/libcudart.so.11.0' if not IS_WINDOWS_PLATFORM else '%CONDA_PREFIX%\\lib\\cudart64_110.dll')
+CUDA_SHARED_LIB_NAME: str = "libcuda.so" if not IS_WINDOWS_PLATFORM else f"{os.environ['SystemRoot']}\\System32\\nvcuda.dll"
+SHARED_LIB_EXTENSION: str = ".so" if not IS_WINDOWS_PLATFORM else ".dll"
+class CUDASetup:
+    _instance = None
+
+    def __init__(self):
+        raise RuntimeError("Call get_instance() instead")
+
+    def generate_instructions(self):
+        if getattr(self, 'error', False): return
+        print(self.error)
+        self.error = True
+        if self.cuda is None:
+            self.add_log_entry('CUDA SETUP: Problem: The main issue seems to be that the main CUDA library was not detected.')
+            self.add_log_entry('CUDA SETUP: Solution 1): Your paths are probably not up-to-date. You can update them via: sudo ldconfig.')
+            self.add_log_entry('CUDA SETUP: Solution 2): If you do not have sudo rights, you can do the following:')
+            self.add_log_entry('CUDA SETUP: Solution 2a): Find the cuda library via: find / -name libcuda.so 2>/dev/null')
+            self.add_log_entry('CUDA SETUP: Solution 2b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_2a')
+            self.add_log_entry('CUDA SETUP: Solution 2c): For a permanent solution add the export from 2b into your .bashrc file, located at ~/.bashrc')
+            return
+
+        if self.cudart_path is None:
+            self.add_log_entry('CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.')
+            self.add_log_entry('CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable')
+            self.add_log_entry('CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null')
+            self.add_log_entry('CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a')
+            self.add_log_entry('CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc')
+            self.add_log_entry('CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.')
+            self.add_log_entry('CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh')
+            self.add_log_entry('CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.')
+            self.add_log_entry('CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local')
+            return
+
+        make_cmd = f'CUDA_VERSION={self.cuda_version_string}'
+        if len(self.cuda_version_string) < 3:
+            make_cmd += ' make cuda92'
+        elif self.cuda_version_string == '110':
+            make_cmd += ' make cuda110'
+        elif self.cuda_version_string[:2] == '11' and int(self.cuda_version_string[2]) > 0:
+            make_cmd += ' make cuda11x'
+        elif self.cuda_version_string == '100':
+            self.add_log_entry('CUDA SETUP: CUDA 10.0 not supported. Please use a different CUDA version.')
+            self.add_log_entry('CUDA SETUP: Before you try again running bitsandbytes, make sure old CUDA 10.0 versions are uninstalled and removed from $LD_LIBRARY_PATH variables.')
+            return
+
+
+        has_cublaslt = is_cublasLt_compatible(self.cc)
+        if not has_cublaslt:
+            make_cmd += '_nomatmul'
+
+        self.add_log_entry('CUDA SETUP: Something unexpected happened. Please compile from source:')
+        self.add_log_entry('git clone git@github.com:TimDettmers/bitsandbytes.git')
+        self.add_log_entry('cd bitsandbytes')
+        self.add_log_entry(make_cmd)
+        self.add_log_entry('python setup.py install')
+
+    def initialize(self):
+        if not getattr(self, 'initialized', False):
+            self.has_printed = False
+            self.lib = None
+            self.initialized = False
+            self.error = False
+
+    def run_cuda_setup(self):
+        self.initialized = True
+        self.cuda_setup_log = []
+
+        binary_name, cudart_path, cuda, cc, cuda_version_string = evaluate_cuda_setup()
+        self.cudart_path = cudart_path
+        self.cuda = cuda
+        self.cc = cc
+        self.cuda_version_string = cuda_version_string
+
+        package_dir = Path(__file__).parent.parent
+        binary_path = package_dir / binary_name
+
+        print('bin', binary_path)
+
+        try:
+            if not binary_path.exists():
+                self.add_log_entry(f"CUDA SETUP: Required library version not found: {binary_name}. Maybe you need to compile it from source?")
+                legacy_binary_name = "libbitsandbytes_cpu" + SHARED_LIB_EXTENSION
+                self.add_log_entry(f"CUDA SETUP: Defaulting to {legacy_binary_name}...")
+                binary_path = package_dir / legacy_binary_name
+                if not binary_path.exists() or torch.cuda.is_available():
+                    self.add_log_entry('')
+                    self.add_log_entry('='*48 + 'ERROR' + '='*37)
+                    self.add_log_entry('CUDA SETUP: CUDA detection failed! Possible reasons:')
+                    self.add_log_entry('1. CUDA driver not installed')
+                    self.add_log_entry('2. CUDA not installed')
+                    self.add_log_entry('3. You have multiple conflicting CUDA libraries')
+                    self.add_log_entry('4. Required library not pre-compiled for this bitsandbytes release!')
+                    self.add_log_entry('CUDA SETUP: If you compiled from source, try again with `make CUDA_VERSION=DETECTED_CUDA_VERSION` for example, `make CUDA_VERSION=113`.')
+                    self.add_log_entry('CUDA SETUP: The CUDA version for the compile might depend on your conda install. Inspect CUDA version via `conda list | grep cuda`.')
+                    self.add_log_entry('='*80)
+                    self.add_log_entry('')
+                    self.generate_instructions()
+                    raise Exception('CUDA SETUP: Setup Failed!')
+                self.lib = ct.cdll.LoadLibrary(str(binary_path))
+            else:
+                self.add_log_entry(f"CUDA SETUP: Loading binary {binary_path}...")
+                self.lib = ct.cdll.LoadLibrary(str(binary_path))
+        except Exception as ex:
+            self.add_log_entry(str(ex))
+
+    def add_log_entry(self, msg, is_warning=False):
+        self.cuda_setup_log.append((msg, is_warning))
+
+    def print_log_stack(self):
+        for msg, is_warning in self.cuda_setup_log:
+            if is_warning:
+                warn(msg)
+            else:
+                print(msg)
+
+    @classmethod
+    def get_instance(cls):
+        if cls._instance is None:
+            cls._instance = cls.__new__(cls)
+            cls._instance.initialize()
+        return cls._instance
+
+
+def is_cublasLt_compatible(cc):
+    has_cublaslt = False
+    if cc is not None:
+        cc_major, cc_minor = cc.split('.')
+        if int(cc_major) < 7 or (int(cc_major) == 7 and int(cc_minor) < 5):
+            CUDASetup.get_instance().add_log_entry("WARNING: Compute capability < 7.5 detected! Only slow 8-bit matmul is supported for your GPU!", is_warning=True)
+        else:
+            has_cublaslt = True
+    return has_cublaslt
+
+def extract_candidate_paths(paths_list_candidate: str) -> Set[Path]:
+    return {Path(ld_path) for ld_path in paths_list_candidate.split(PATH_COLLECTION_SEPARATOR) if ld_path}
+
+
+def remove_non_existent_dirs(candidate_paths: Set[Path]) -> Set[Path]:
+    existent_directories: Set[Path] = set()
+    for path in candidate_paths:
+        try:
+            if path.exists():
+                existent_directories.add(path)
+        except OSError as exc:
+            if exc.errno != errno.ENAMETOOLONG:
+                raise exc
+
+    non_existent_directories: Set[Path] = candidate_paths - existent_directories
+    if non_existent_directories:
+        CUDASetup.get_instance().add_log_entry("WARNING: The following directories listed in your path were found to "
+            f"be non-existent: {non_existent_directories}", is_warning=True)
+
+    return existent_directories
+
+
+def get_cuda_runtime_lib_paths(candidate_paths: Set[Path]) -> Set[Path]:
+    paths = set()
+    for libname in CUDA_RUNTIME_LIBS:
+        for path in candidate_paths:
+            if (path / libname).is_file():
+                paths.add(path / libname)
+    return paths
+
+
+def resolve_paths_list(paths_list_candidate: str) -> Set[Path]:
+    """
+    Searches a given environmental var for the CUDA runtime library,
+    i.e. `libcudart.so`.
+    """
+    return remove_non_existent_dirs(extract_candidate_paths(paths_list_candidate))
+
+
+def find_cuda_lib_in(paths_list_candidate: str) -> Set[Path]:
+    return get_cuda_runtime_lib_paths(
+        resolve_paths_list(paths_list_candidate)
+    )
+
+
+def warn_in_case_of_duplicates(results_paths: Set[Path]) -> None:
+    if len(results_paths) > 1:
+        warning_msg = (
+            f"Found duplicate {CUDA_RUNTIME_LIBS} files: {results_paths}.. "
+            "We'll flip a coin and try one of these, in order to fail forward.\n"
+            "Either way, this might cause trouble in the future:\n"
+            "If you get `CUDA error: invalid device function` errors, the above "
+            "might be the cause and the solution is to make sure only one "
+            f"{CUDA_RUNTIME_LIBS} in the paths that we search based on your env.")
+        CUDASetup.get_instance().add_log_entry(warning_msg, is_warning=True)
+
+
+def determine_cuda_runtime_lib_path() -> Union[Path, None]:
+    """
+        Searches for a cuda installations, in the following order of priority:
+            1. active conda env
+            2. LD_LIBRARY_PATH
+            3. any other env vars, while ignoring those that
+                - are known to be unrelated (see `bnb.cuda_setup.env_vars.to_be_ignored`)
+                - don't contain the path separator `/`
+
+        If multiple libraries are found in part 3, we optimistically try one,
+        while giving a warning message.
+    """
+    candidate_env_vars = get_potentially_lib_path_containing_env_vars()
+
+    if "CONDA_PREFIX" in candidate_env_vars:
+        conda_libs_path = Path(candidate_env_vars["CONDA_PREFIX"]) / "bin"
+
+        conda_cuda_libs = find_cuda_lib_in(str(conda_libs_path))
+        warn_in_case_of_duplicates(conda_cuda_libs)
+
+        if conda_cuda_libs:
+            return next(iter(conda_cuda_libs))
+        
+        conda_libs_path = Path(candidate_env_vars["CONDA_PREFIX"]) / "lib"
+
+        conda_cuda_libs = find_cuda_lib_in(str(conda_libs_path))
+        warn_in_case_of_duplicates(conda_cuda_libs)
+
+        if conda_cuda_libs:
+            return next(iter(conda_cuda_libs))
+        CUDASetup.get_instance().add_log_entry(f'{candidate_env_vars["CONDA_PREFIX"]} did not contain '
+            f'{CUDA_RUNTIME_LIBS} as expected! Searching further paths...', is_warning=True)
+        
+    if "CUDA_PATH" in candidate_env_vars:
+        ld_cuda_libs_path = Path(candidate_env_vars["CUDA_PATH"]) / "bin"
+    
+        lib_ld_cuda_libs = find_cuda_lib_in(str(ld_cuda_libs_path))
+        warn_in_case_of_duplicates(lib_ld_cuda_libs)
+
+        if lib_ld_cuda_libs:
+            return next(iter(lib_ld_cuda_libs))
+
+        ld_cuda_libs_path = Path(candidate_env_vars["CUDA_PATH"]) / "lib"
+    
+        lib_ld_cuda_libs = find_cuda_lib_in(str(ld_cuda_libs_path))
+        warn_in_case_of_duplicates(lib_ld_cuda_libs)
+
+        if lib_ld_cuda_libs:
+            return next(iter(lib_ld_cuda_libs))
+
+        CUDASetup.get_instance().add_log_entry(f'{candidate_env_vars["CUDA_PATH"]} did not contain '
+            f'{CUDA_RUNTIME_LIBS} as expected! Searching further paths...', is_warning=True)
+        
+    if "CUDA_HOME" in candidate_env_vars:
+        ld_cuda_libs_path = Path(candidate_env_vars["CUDA_HOME"]) / "bin"
+    
+        lib_ld_cuda_libs = find_cuda_lib_in(str(ld_cuda_libs_path))
+        warn_in_case_of_duplicates(lib_ld_cuda_libs)
+
+        if lib_ld_cuda_libs:
+            return next(iter(lib_ld_cuda_libs))
+        
+        ld_cuda_libs_path = Path(candidate_env_vars["CUDA_HOME"]) / "lib"
+    
+        lib_ld_cuda_libs = find_cuda_lib_in(str(ld_cuda_libs_path))
+        warn_in_case_of_duplicates(lib_ld_cuda_libs)
+
+        if lib_ld_cuda_libs:
+            return next(iter(lib_ld_cuda_libs))
+
+        CUDASetup.get_instance().add_log_entry(f'{candidate_env_vars["CUDA_HOME"]} did not contain '
+            f'{CUDA_RUNTIME_LIBS} as expected! Searching further paths...', is_warning=True)
+
+    if "LD_LIBRARY_PATH" in candidate_env_vars:
+        lib_ld_cuda_libs = find_cuda_lib_in(candidate_env_vars["LD_LIBRARY_PATH"])
+        warn_in_case_of_duplicates(lib_ld_cuda_libs)
+
+        if lib_ld_cuda_libs:
+            return next(iter(lib_ld_cuda_libs))
+
+        CUDASetup.get_instance().add_log_entry(f'{candidate_env_vars["LD_LIBRARY_PATH"]} did not contain '
+            f'{CUDA_RUNTIME_LIBS} as expected! Searching further paths...', is_warning=True)
+        
+    if "PATH" in candidate_env_vars:
+        lib_ld_cuda_libs = find_cuda_lib_in(candidate_env_vars["PATH"])
+        warn_in_case_of_duplicates(lib_ld_cuda_libs)
+
+        if lib_ld_cuda_libs:
+            return next(iter(lib_ld_cuda_libs))
+
+        CUDASetup.get_instance().add_log_entry(f'{candidate_env_vars["PATH"]} did not contain '
+            f'{CUDA_RUNTIME_LIBS} as expected! Searching further paths...', is_warning=True)
+        
+    remaining_candidate_env_vars = {
+        env_var: value for env_var, value in candidate_env_vars.items()
+        if env_var not in {"CONDA_PREFIX", "CUDA_HOME", "CUDA_PATH", "LD_LIBRARY_PATH", "PATH"}
+    }
+
+    cuda_runtime_libs = set()
+    for env_var, value in remaining_candidate_env_vars.items():
+        cuda_runtime_libs.update(find_cuda_lib_in(value))
+
+    if len(cuda_runtime_libs) == 0:
+        CUDASetup.get_instance().add_log_entry('CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...')
+        cuda_runtime_libs.update(find_cuda_lib_in('/usr/local/cuda/lib64'))
+
+    warn_in_case_of_duplicates(cuda_runtime_libs)
+
+    return next(iter(cuda_runtime_libs)) if cuda_runtime_libs else None
 
 
 def check_cuda_result(cuda, result_val):
     # 3. Check for CUDA errors
     if result_val != 0:
-        error_str = ctypes.c_char_p()
+        error_str = ct.c_char_p()
-        cuda.cuGetErrorString(result_val, ctypes.byref(error_str))
+        cuda.cuGetErrorString(result_val, ct.byref(error_str))
-        print(f"CUDA exception! Error code: {error_str.value.decode()}")
+        if error_str.value is not None:
+            CUDASetup.get_instance().add_log_entry(f"CUDA exception! Error code: {error_str.value.decode()}")
+        else:
+            CUDASetup.get_instance().add_log_entry(f"Unknown CUDA exception! Please check your CUDA install. It might also be that your GPU is too old.")
+
 
-def get_cuda_version(cuda, cudart_path):
 # https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART____VERSION.html#group__CUDART____VERSION
+def get_cuda_version(cuda, cudart_path):
+    if cuda is None: return None
+
     try:
-        cudart = ctypes.CDLL(cudart_path)
+        cudart = ct.CDLL(str(cudart_path))
     except OSError:
-        # TODO: shouldn't we error or at least warn here?
+        CUDASetup.get_instance().add_log_entry(f'ERROR: libcudart.so could not be read from path: {cudart_path}!')
-        print(f'ERROR: libcudart.so could not be read from path: {cudart_path}!')
         return None
 
-    version = ctypes.c_int()
+    version = ct.c_int()
-    check_cuda_result(cuda, cudart.cudaRuntimeGetVersion(ctypes.byref(version)))
+    try:
+        check_cuda_result(cuda, cudart.cudaRuntimeGetVersion(ct.byref(version)))
+    except AttributeError as e:
+        CUDASetup.get_instance().add_log_entry(f'ERROR: {str(e)}')
+        CUDASetup.get_instance().add_log_entry(f'CUDA SETUP: libcudart.so path is {cudart_path}')
+        CUDASetup.get_instance().add_log_entry(f'CUDA SETUP: Is seems that your cuda installation is not in your path. See https://github.com/TimDettmers/bitsandbytes/issues/85 for more information.')
     version = int(version.value)
     major = version//1000
     minor = (version-(major*1000))//10
 
     if major < 11:
-       print('CUDA SETUP: CUDA version lower than 11 are currently not supported for LLM.int8(). You will be only to use 8-bit optimizers and quantization routines!!')
+        CUDASetup.get_instance().add_log_entry('CUDA SETUP: CUDA version lower than 11 are currently not supported for LLM.int8(). You will be only to use 8-bit optimizers and quantization routines!!')
 
     return f'{major}{minor}'
 
@@ -52,10 +384,9 @@ def get_cuda_version(cuda, cudart_path):
 def get_cuda_lib_handle():
     # 1. find libcuda.so library (GPU driver) (/usr/lib)
     try:
-        cuda = ctypes.CDLL("libcuda.so")
+        cuda = ct.CDLL(CUDA_SHARED_LIB_NAME)
     except OSError:
-        # TODO: shouldn't we error or at least warn here?
+        CUDASetup.get_instance().add_log_entry('CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!')
-        print('CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!')
         return None
     check_cuda_result(cuda, cuda.cuInit(0))
 
@@ -73,23 +404,20 @@ def get_compute_capabilities(cuda):
     # bits taken from https://gist.github.com/f0k/63a664160d016a491b2cbea15913d549
     """
 
+    nGpus = ct.c_int()
+    cc_major = ct.c_int()
+    cc_minor = ct.c_int()
 
-    nGpus = ctypes.c_int()
+    device = ct.c_int()
-    cc_major = ctypes.c_int()
-    cc_minor = ctypes.c_int()
 
-    device = ctypes.c_int()
+    check_cuda_result(cuda, cuda.cuDeviceGetCount(ct.byref(nGpus)))
-
-    check_cuda_result(cuda, cuda.cuDeviceGetCount(ctypes.byref(nGpus)))
     ccs = []
     for i in range(nGpus.value):
-        check_cuda_result(cuda, cuda.cuDeviceGet(ctypes.byref(device), i))
+        check_cuda_result(cuda, cuda.cuDeviceGet(ct.byref(device), i))
-        ref_major = ctypes.byref(cc_major)
+        ref_major = ct.byref(cc_major)
-        ref_minor = ctypes.byref(cc_minor)
+        ref_minor = ct.byref(cc_minor)
         # 2. call extern C function to determine CC
-        check_cuda_result(
+        check_cuda_result(cuda, cuda.cuDeviceComputeCapability(ref_major, ref_minor, device))
-            cuda, cuda.cuDeviceComputeCapability(ref_major, ref_minor, device)
-        )
         ccs.append(f"{cc_major.value}.{cc_minor.value}")
 
     return ccs
@@ -102,48 +430,49 @@ def get_compute_capability(cuda):
     capabilities are downwards compatible. If no GPUs are detected, it returns
     None.
     """
-    ccs = get_compute_capabilities(cuda)
+    if cuda is None: return None
-    if ccs is not None:
+
     # TODO: handle different compute capabilities; for now, take the max
-        return ccs[-1]
+    ccs = get_compute_capabilities(cuda)
-    return None
+    if ccs: return ccs[-1]
 
 
 def evaluate_cuda_setup():
+    if 'BITSANDBYTES_NOWELCOME' not in os.environ or str(os.environ['BITSANDBYTES_NOWELCOME']) == '0':
         print('')
         print('='*35 + 'BUG REPORT' + '='*35)
-    print('Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues')
+        print(('Welcome to bitsandbytes. For bug reports, please run\n\npython -m bitsandbytes\n\n'),
-    print('For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link')
+              ('and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues'))
         print('='*80)
-    return "libbitsandbytes_cuda116.dll"            # $$$
+        return 'libbitsandbytes_cuda118.dll', None, None, None, None
-    
+    if not torch.cuda.is_available(): return 'libbitsandbytes_cpu'+SHARED_LIB_EXTENSION, None, None, None, None
-    binary_name = "libbitsandbytes_cpu.so"
-    #if not torch.cuda.is_available():
-        #print('No GPU detected. Loading CPU library...')
-        #return binary_name
 
+    cuda_setup = CUDASetup.get_instance()
     cudart_path = determine_cuda_runtime_lib_path()
-    if cudart_path is None:
-        print(
-            "WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)!"
-        )
-        return binary_name
-
-    print(f"CUDA SETUP: CUDA runtime path found: {cudart_path}")
     cuda = get_cuda_lib_handle()
     cc = get_compute_capability(cuda)
-    print(f"CUDA SETUP: Highest compute capability among GPUs detected: {cc}")
     cuda_version_string = get_cuda_version(cuda, cudart_path)
 
+    failure = False
+    if cudart_path is None:
+        failure = True
+        cuda_setup.add_log_entry("WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)!", is_warning=True)
+    else:
+        cuda_setup.add_log_entry(f"CUDA SETUP: CUDA runtime path found: {cudart_path}")
 
-    if cc == '':
+    if cc == '' or cc is None:
-        print(
+        failure = True
-            "WARNING: No GPU detected! Check your CUDA paths. Processing to load CPU-only library..."
+        cuda_setup.add_log_entry("WARNING: No GPU detected! Check your CUDA paths. Proceeding to load CPU-only library...", is_warning=True)
-        )
+    else:
-        return binary_name
+        cuda_setup.add_log_entry(f"CUDA SETUP: Highest compute capability among GPUs detected: {cc}")
+
+    if cuda is None:
+        failure = True
+    else:
+        cuda_setup.add_log_entry(f'CUDA SETUP: Detected CUDA version {cuda_version_string}')
 
     # 7.5 is the minimum CC vor cublaslt
-    has_cublaslt = cc in ["7.5", "8.0", "8.6"]
+    has_cublaslt = is_cublasLt_compatible(cc)
 
     # TODO:
     # (1) CUDA missing cases (no CUDA installed by CUDA driver (nvidia-smi accessible)
@@ -151,16 +480,13 @@ def evaluate_cuda_setup():
 
     # we use ls -l instead of nvcc to determine the cuda version
     # since most installations will have the libcudart.so installed, but not the compiler
-    print(f'CUDA SETUP: Detected CUDA version {cuda_version_string}')
 
-    def get_binary_name():
+    if failure:
-        "if not has_cublaslt (CC < 7.5), then we have to choose  _nocublaslt.so"
+        binary_name = "libbitsandbytes_cpu" + SHARED_LIB_EXTENSION
-        bin_base_name = "libbitsandbytes_cuda"
+    elif has_cublaslt:
-        if has_cublaslt:
+        binary_name = f"libbitsandbytes_cuda{cuda_version_string}" + SHARED_LIB_EXTENSION
-            return f"{bin_base_name}{cuda_version_string}.so"
     else:
-            return f"{bin_base_name}{cuda_version_string}_nocublaslt.so"
+        "if not has_cublaslt (CC < 7.5), then we have to choose  _nocublaslt"
+        binary_name = f"libbitsandbytes_cuda{cuda_version_string}_nocublaslt" +  SHARED_LIB_EXTENSION
 
-    binary_name = get_binary_name()
+    return binary_name, cudart_path, cuda, cc, cuda_version_string
-
-    return binary_name

library/train_util.py

@@ -2165,6 +2165,8 @@ def cache_batch_latents(
             info.latents = latent
             if flip_aug:
                 info.latents_flipped = flipped_latent
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
 
 
 def cache_batch_text_encoder_outputs(

requirements.txt

@@ -6,7 +6,7 @@ albumentations==1.3.0
 opencv-python==4.7.0.68
 einops==0.6.0
 pytorch-lightning==1.9.0
-bitsandbytes==0.35.0
+bitsandbytes==0.39.1
 tensorboard==2.10.1
 safetensors==0.3.1
 # gradio==3.16.2