Remove legacy sparse functionality (#1881)

Author: matthewdouglas

.github/workflows/python-package.yml

@@ -86,7 +86,7 @@ jobs:
           cuda: ${{ matrix.cuda_version }}
           method: "network"
           # The "crt" "nvvm" and "nvptxcompiler" components are added for CUDA 13.
-          sub-packages: ${{ format('["nvcc"{0},"cudart","cusparse","cublas","thrust","cublas_dev","cusparse_dev"]', startsWith(matrix.cuda_version, '13.') && ',"crt","nvvm","nvptxcompiler"' || '') }}
+          sub-packages: ${{ format('["nvcc"{0},"cudart","cublas","thrust","cublas_dev"]', startsWith(matrix.cuda_version, '13.') && ',"crt","nvvm","nvptxcompiler"' || '') }}
           use-github-cache: false
           use-local-cache: false
           log-file-suffix: ${{matrix.os}}-${{matrix.cuda_version}}.txt

.github/workflows/test-runner.yml

@@ -148,7 +148,7 @@ jobs:
         with:
           cuda: ${{ inputs.cuda_version }}
           method: "network"
-          sub-packages: '["nvcc","cudart","cusparse","cublas","thrust","nvrtc_dev","cublas_dev","cusparse_dev"]'
+          sub-packages: '["nvcc","cudart","cublas","thrust","nvrtc_dev","cublas_dev"]'
           use-github-cache: false
 
       # Windows: Setup MSVC (needed for both CPU and CUDA builds)

CMakeLists.txt

@@ -349,7 +349,7 @@ endif()
 
 if(BUILD_CUDA)
     target_include_directories(bitsandbytes PUBLIC ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES})
-    target_link_libraries(bitsandbytes PUBLIC CUDA::cudart CUDA::cublas CUDA::cublasLt CUDA::cusparse)
+    target_link_libraries(bitsandbytes PUBLIC CUDA::cudart CUDA::cublas CUDA::cublasLt)
     set_target_properties(bitsandbytes
         PROPERTIES
             CUDA_SEPARABLE_COMPILATION ON
@@ -369,7 +369,6 @@ if(BUILD_HIP)
     endmacro()
     find_package_and_print_version(hipblas REQUIRED)
     find_package_and_print_version(hiprand REQUIRED)
-    find_package_and_print_version(hipsparse REQUIRED)
 
     ## hacky way of excluding hip::amdhip64 (with it linked many tests unexpectedly fail e.g. adam8bit because of inaccuracies)
     ## On Windows, we need to link amdhip64 explicitly
@@ -381,7 +380,7 @@ if(BUILD_HIP)
 
     target_include_directories(bitsandbytes PRIVATE ${CMAKE_SOURCE_DIR} ${CMAKE_SOURCE_DIR}/include ${ROCM_PATH}/include /include)
     target_link_directories(bitsandbytes PRIVATE ${ROCM_PATH}/lib /lib)
-    target_link_libraries(bitsandbytes PUBLIC roc::hipblas hip::hiprand roc::hipsparse)
+    target_link_libraries(bitsandbytes PUBLIC roc::hipblas hip::hiprand)
 
     # On Windows, rocblas is not pulled in transitively by roc::hipblas
     # and is needed because ops_hip.cuh uses rocblas_handle directly.

agents/api_surface.md

@@ -860,57 +860,7 @@ F.batched_igemm(
 Batched int8 matrix multiplication.
 **Stability:** Stable (internal).
 
-### 4.9 Sparse Operations
-
-#### `COOSparseTensor`
-
-```python
-class F.COOSparseTensor:
-    def __init__(self, rows, cols, nnz, rowidx, colidx, values): ...
-```
-
-**Stability:** Legacy — used internally for sparse decomposition.
-
-#### `CSRSparseTensor` / `CSCSparseTensor`
-
-Similar sparse tensor containers.
-**Stability:** Legacy.
-
-#### `coo_zeros`
-
-```python
-F.coo_zeros(rows, cols, nnz, device, dtype=torch.half) -> COOSparseTensor
-```
-
-#### `coo2csr` / `coo2csc`
-
-```python
-F.coo2csr(cooA: COOSparseTensor) -> CSRSparseTensor
-F.coo2csc(cooA: COOSparseTensor) -> CSCSparseTensor
-```
-
-#### `spmm_coo`
-
-```python
-F.spmm_coo(
-    cooA: COOSparseTensor, B: torch.Tensor,
-    out: Optional[torch.Tensor] = None,
-) -> torch.Tensor
-```
-
-Sparse matrix-dense matrix multiply using cusparse.
-**Stability:** Legacy.
-
-#### `spmm_coo_very_sparse`
-
-```python
-F.spmm_coo_very_sparse(cooA, B, dequant_stats=None, out=None) -> torch.Tensor
-```
-
-Optimized for very sparse matrices with custom kernel.
-**Stability:** Legacy.
-
-### 4.10 Paged Memory
+### 4.9 Paged Memory
 
 #### `get_paged`
 
@@ -930,7 +880,7 @@ F.prefetch_tensor(A: torch.Tensor, to_cpu: bool = False) -> None
 Prefetch a paged tensor to GPU or CPU.
 **Stability:** Stable (internal).
 
-### 4.11 CPU-Specific Functions
+### 4.10 CPU-Specific Functions
 
 #### `_convert_weight_packed_for_cpu`
 
@@ -963,7 +913,7 @@ F.has_avx512bf16() -> bool
 Detects AVX512BF16 CPU support.
 **Stability:** Internal but may be useful externally.
 
-### 4.12 Utility Functions
+### 4.11 Utility Functions
 
 #### `is_on_gpu`
 
@@ -983,7 +933,7 @@ F.get_ptr(A: Optional[Tensor]) -> Optional[ct.c_void_p]
 Gets the data pointer of a tensor for ctypes calls.
 **Stability:** Internal.
 
-### 4.13 Singleton Managers
+### 4.12 Singleton Managers
 
 #### `GlobalPageManager`
 
@@ -1003,15 +953,6 @@ F.CUBLAS_Context.get_instance() -> CUBLAS_Context
 Manages cuBLAS context handles per device.
 **Stability:** Internal.
 
-#### `Cusparse_Context`
-
-```python
-F.Cusparse_Context.get_instance() -> Cusparse_Context
-```
-
-Manages cusparse context handle.
-**Stability:** Internal.
-
 ---
 
 ## 5. Autograd Functions
@@ -1234,7 +1175,7 @@ bitsandbytes.utils.replace_linear(
 | Class | Description |
 |-------|-------------|
 | `BNBNativeLibrary` | Base wrapper for the ctypes-loaded native library |
-| `CudaBNBNativeLibrary` | CUDA-specific subclass (sets up context/cusparse/managed ptr) |
+| `CudaBNBNativeLibrary` | CUDA-specific subclass (sets up context/managed ptr) |
 | `ErrorHandlerMockBNBNativeLibrary` | Fallback mock that defers error messages to call time |
 
 ### Module-level symbols
@@ -1396,11 +1337,9 @@ A PR that changes any of these symbols MUST consider downstream impact:
 
 - `bitsandbytes.cextension.*` (native library loading)
 - `bitsandbytes.functional.get_ptr`, `is_on_gpu`, `_get_tensor_stream`
-- `bitsandbytes.functional.GlobalPageManager`, `CUBLAS_Context`, `Cusparse_Context`
+- `bitsandbytes.functional.GlobalPageManager`, `CUBLAS_Context`
 - `bitsandbytes.functional._convert_weight_packed_for_cpu*`
 - `bitsandbytes.functional.check_matmul`, `elementwise_func`, `fill`, `_mul`
-- `bitsandbytes.functional.spmm_coo`, `spmm_coo_very_sparse`
-- `bitsandbytes.functional.COOSparseTensor`, `CSRSparseTensor`, `CSCSparseTensor`
 - `bitsandbytes.utils.pack_dict_to_tensor`, `unpack_tensor_to_dict`
 - `bitsandbytes.utils.execute_and_return`, `sync_gpu`
 - `bitsandbytes.optim.optimizer.MockArgs`

agents/architecture_guide.md

@@ -962,8 +962,8 @@ The `COMPUTE_BACKEND` CMake variable selects the target:
 | Backend | Library name | Languages | Dependencies |
 |---|---|---|---|
 | `cpu` | `libbitsandbytes_cpu.so` | C++17 | OpenMP (optional) |
-| `cuda` | `libbitsandbytes_cuda{VER}.so` | C++17 + CUDA | cudart, cublas, cublasLt, cusparse |
-| `hip` | `libbitsandbytes_rocm{VER}.so` | C++17 + HIP | hipblas, hiprand, hipsparse |
+| `cuda` | `libbitsandbytes_cuda{VER}.so` | C++17 + CUDA | cudart, cublas, cublasLt |
+| `hip` | `libbitsandbytes_rocm{VER}.so` | C++17 + HIP | hipblas, hiprand |
 | `mps` | `libbitsandbytes_mps.dylib` | C++17 + ObjC++ | Metal framework |
 | `xpu` | `libbitsandbytes_xpu.so` | C++20 + SYCL | Intel oneAPI |
 

agents/code_standards.md

@@ -152,7 +152,7 @@ class GlobalOptimManager:
 ```
 
 This pattern is used by: `GlobalOptimManager`, `GlobalPageManager`, `CUBLAS_Context`,
-`Cusparse_Context`, `GlobalOutlierPooler`, `OutlierTracer`.
+`GlobalOutlierPooler`, `OutlierTracer`.
 
 ---
 
@@ -867,7 +867,6 @@ Use the project's error checking macros:
 
 ```cpp
 CUDA_CHECK_RETURN(cudaMemcpy(...));
-CHECK_CUSPARSE(cusparseCreate(...));
 ```
 
 The `checkCublasStatus` function returns an error code rather than throwing — the Python

agents/issue_patterns.md

@@ -34,9 +34,9 @@ These are the single largest category of issues. Most are environment problems o
 >
 > If you're still hitting problems on the **latest** bitsandbytes (v0.45+), please open a new issue with the output of `python -m bitsandbytes` and your environment details.
 
-### Missing `libcusparse.so.11` / shared library mismatch
+### Missing shared CUDA library / shared library mismatch
 
-**How to identify:** `OSError: libcusparse.so.11: cannot open shared object file: No such file or directory`. Or similar errors for `libcusparse.so.12`, `libcublasLt.so.11`, etc.
+**How to identify:** `OSError: libcublasLt.so.11: cannot open shared object file: No such file or directory`. Or similar errors for `libcudart`, `libcublas`, etc.
 
 **What happened:** The bnb binary was compiled against one CUDA version (e.g., 11.x) but the system only has another (e.g., 12.x). The shared library dependencies don't exist. Modern releases ship platform-specific wheels with better CUDA version detection and multiple binary variants.
 

bitsandbytes/backends/cuda/ops.py

@@ -171,7 +171,7 @@ def _(
     A: torch.Tensor,
     threshold=0.0,
 ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, Optional[torch.Tensor]]:
-    # Use CUDA kernel for rowwise and COO tensor
+    # Use CUDA kernel for rowwise quant and outlier column detection
     quant_row, row_stats, outlier_cols = torch.ops.bitsandbytes.int8_vectorwise_quant.default(
         A,
         threshold=threshold,

bitsandbytes/cextension.py

@@ -90,7 +90,6 @@ class CudaBNBNativeLibrary(BNBNativeLibrary):
     def __init__(self, lib: ct.CDLL):
         super().__init__(lib)
         lib.get_context.restype = ct.c_void_p
-        lib.get_cusparse.restype = ct.c_void_p
         lib.cget_managed_ptr.restype = ct.c_void_p