Merge branch 'main' into main

Author: TimDettmers

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,32 @@
+name: "\U0001F41B Bug Report"
+description: Submit a bug report to help us improve bitsandbytes
+body:
+  - type: textarea
+    id: system-info
+    attributes:
+      label: System Info
+      description: Please share your relevant system information with us
+      placeholder: platform, python version, hardware, ...
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduction
+    validations:
+      required: true
+    attributes:
+      label: Reproduction
+      description: |
+        Please provide a code sample that reproduces the problem you ran into. It can be a Colab link or just a code snippet.
+        Please provide the simplest reproducer as possible so that we can quickly fix the issue. 
+
+      placeholder: |
+        Reproducer: 
+   
+  - type: textarea
+    id: expected-behavior
+    validations:
+      required: true
+    attributes:
+      label: Expected behavior
+      description: "A clear and concise description of what you would expect to happen."

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,30 @@
+name: "\U0001F680 Feature request"
+description: Submit a proposal/request for a new feature
+labels: [ "feature" ]
+body:
+  - type: textarea
+    id: feature-request
+    validations:
+      required: true
+    attributes:
+      label: Feature request
+      description: |
+        A clear and concise description of the feature proposal.
+
+  - type: textarea
+    id: motivation
+    validations:
+      required: true
+    attributes:
+      label: Motivation
+      description: |
+        Please outline the motivation for the proposal. Is your feature request related to a problem? 
+
+  - type: textarea
+    id: contribution
+    validations:
+      required: true
+    attributes:
+      label: Your contribution
+      description: |
+        Is there any way that you could help, e.g. by submitting a PR? 

.github/workflows/stale.yml

@@ -0,0 +1,27 @@
+name: Stale Bot
+
+on:
+  schedule:
+    - cron: "0 15 * * *"
+
+jobs:
+  close_stale_issues:
+    name: Close Stale Issues
+    if: github.repository == 'TimDettmers/bitsandbytes'
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Setup Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: 3.8
+
+    - name: Install requirements
+      run: |
+        pip install PyGithub
+    - name: Close stale issues
+      run: |
+        python scripts/stale.py

.gitignore

@@ -133,3 +133,4 @@ dmypy.json
 
 dependencies
 cuda_build
+.vscode/*

.style.yapf

@@ -0,0 +1,13 @@
+[style]
+ALIGN_CLOSING_BRACKET_WITH_VISUAL_INDENT = True
+ALLOW_MULTILINE_LAMBDAS = True
+BLANK_LINE_BEFORE_NESTED_CLASS_OR_DEF = True
+COLUMN_LIMIT = 88
+COALESCE_BRACKETS = True
+SPACE_BETWEEN_ENDING_COMMA_AND_CLOSING_BRACKET = True
+SPACES_BEFORE_COMMENT = 2
+SPLIT_BEFORE_BITWISE_OPERATOR = True
+SPLIT_BEFORE_FIRST_ARGUMENT = True
+SPLIT_BEFORE_LOGICAL_OPERATOR = True
+SPLIT_BEFORE_NAMED_ASSIGNS = True
+SPLIT_COMPLEX_COMPREHENSION = True

CHANGELOG.md

@@ -311,7 +311,19 @@ User experience:
 Performance:
  - improved 4-bit inference performance for A100 GPUs. This degraded performance for A40/RTX3090 and RTX 4090 GPUs slightly.
 
-### 0.41.0
+### 0.41.1
 
 Bug fixes:
  - Fixed bugs in dynamic exponent data type creation. Thank you @RossM, @KohakuBlueleaf, @ArrowM #659 #227 #262 #152
+
+### 0.41.2
+
+Feature:
+ - 4-bit serialization now supported. This enables 4-bit load/store. Thank you @poedator #753
+
+### 0.41.3
+
+Bug fixes:
+ - Fixed an issue where 4-bit serialization would fail for layers without double quantization #868. Thank you, @poedator
+ - Fixed an issue where calling .to() or .cuda() on a 4-bit layer twice would result in an error #867. Thank you, @jph00
+

README.md

@@ -38,7 +38,7 @@ python setup.py install
 ```python
 from transformers import AutoModelForCausalLM
 model = AutoModelForCausalLM.from_pretrained(
-  'decapoda-research/llama-7b-hf,
+  'decapoda-research/llama-7b-hf',
   device_map='auto',
   load_in_8bit=True,
   max_memory=f'{int(torch.cuda.mem_get_info()[0]/1024**3)-2}GB')
@@ -146,13 +146,13 @@ For upcoming features and changes and full history see [Patch Notes](CHANGELOG.m
 To compile from source, you need an installation of CUDA. If `nvcc` is not installed, you can install the CUDA Toolkit with nvcc through the following commands.
 
 ```bash
-wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/main/cuda_install.sh
+wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/main/install_cuda.sh
 # Syntax cuda_install CUDA_VERSION INSTALL_PREFIX EXPORT_TO_BASH
-#   CUDA_VERSION in {110, 111, 112, 113, 114, 115, 116, 117, 118, 120, 121}
+#   CUDA_VERSION in {110, 111, 112, 113, 114, 115, 116, 117, 118, 120, 121, 122}
 #   EXPORT_TO_BASH in {0, 1} with 0=False and 1=True 
 
-# For example, the following installs CUDA 11.8 to ~/local/cuda-11.8 and exports the path to your .bashrc
-bash cuda install 118 ~/local 1 
+# For example, the following installs CUDA 11.7 to ~/local/cuda-11.7 and exports the path to your .bashrc
+bash install_cuda.sh 117 ~/local 1 
 ```
 
 To use a specific CUDA version just for a single compile run, you can set the variable `CUDA_HOME`, for example the following command compiles `libbitsandbytes_cuda117.so` using compiler flags for cuda11x with the cuda version at `~/local/cuda-11.7`:

bitsandbytes/autograd/_functions.py

@@ -496,15 +496,15 @@ class MatMul4Bit(torch.autograd.Function):
     # backward is mostly the same, but adds one extra clause (see "elif state.CxB is not None")
 
     @staticmethod
-    def forward(ctx, A, B, out=None, bias=None, state=None):
+    def forward(ctx, A, B, out=None, bias=None, quant_state: F.QuantState = None):
         # default of pytorch behavior if inputs are empty
         ctx.is_empty = False
         if prod(A.shape) == 0:
             ctx.is_empty = True
             ctx.A = A
             ctx.B = B
             ctx.bias = bias
-            B_shape = state[1]
+            B_shape = quant_state.shape
             if A.shape[-1] == B_shape[0]:
                 return torch.empty(A.shape[:-1] + B_shape[1:], dtype=A.dtype, device=A.device)
             else:
@@ -513,10 +513,10 @@ def forward(ctx, A, B, out=None, bias=None, state=None):
 
         # 1. Dequantize
         # 2. MatmulnN
-        output = torch.nn.functional.linear(A, F.dequantize_4bit(B, state).to(A.dtype).t(), bias)
+        output = torch.nn.functional.linear(A, F.dequantize_4bit(B, quant_state).to(A.dtype).t(), bias)
 
         # 3. Save state
-        ctx.state = state
+        ctx.state = quant_state
         ctx.dtype_A, ctx.dtype_B, ctx.dtype_bias = A.dtype, B.dtype, None if bias is None else bias.dtype
 
         if any(ctx.needs_input_grad[:2]):
@@ -534,7 +534,6 @@ def backward(ctx, grad_output):
 
         req_gradA, _, _, req_gradBias, _= ctx.needs_input_grad
         A, B = ctx.tensors
-        state = ctx.state
 
         grad_A, grad_B, grad_bias = None, None, None
 
@@ -563,12 +562,11 @@ def matmul(
     return MatMul8bitLt.apply(A, B, out, bias, state)
 
 
-def matmul_4bit(A: tensor, B: tensor, quant_state: List, out: tensor = None, bias=None):
+def matmul_4bit(A: tensor, B: tensor, quant_state: F.QuantState, out: tensor = None, bias=None):
     assert quant_state is not None
     if A.numel() == A.shape[-1] and A.requires_grad == False:
-        absmax, shape, dtype, blocksize, compressed_stats, quant_type, data_type = quant_state
-        if A.shape[-1] % blocksize != 0:
-            warn(f'Some matrices hidden dimension is not a multiple of {blocksize} and efficient inference kernels are not supported for these (slow). Matrix input size found: {A.shape}')
+        if A.shape[-1] % quant_state.blocksize != 0:
+            warn(f'Some matrices hidden dimension is not a multiple of {quant_state.blocksize} and efficient inference kernels are not supported for these (slow). Matrix input size found: {A.shape}')
             return MatMul4Bit.apply(A, B, out, bias, quant_state)
         else:
             out = F.gemv_4bit(A, B.t(), out, state=quant_state)

bitsandbytes/cuda_setup/env_vars.py

@@ -8,6 +8,7 @@ def to_be_ignored(env_var: str, value: str) -> bool:
         "OLDPWD",
         "SSH_AUTH_SOCK",  # SSH stuff, therefore unrelated
         "SSH_TTY",
+        "GOOGLE_VM_CONFIG_LOCK_FILE",  # on GCP setups, requires elevated permissions, causing problems in Jupyter notebooks
         "HOME",  # Linux shell default
         "TMUX",  # Terminal Multiplexer
         "XDG_DATA_DIRS",  # XDG: Desktop environment stuff

bitsandbytes/cuda_setup/main.py

@@ -67,6 +67,7 @@ def generate_instructions(self):
             self.add_log_entry('CUDA SETUP: Solution 2a): Download CUDA install script: wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/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}'