llama.cpp/ggml
Oliver Simons 64ac9ab66a
CUDA : Fix CUB's argsort when nrows % block_size == 0 CCCL < 3.1 (#21181)
* CUDA: Fix CUB's argsort when nrows % block_size == 0 CCCL < 3.1

We wrongly calculated offset_grid as `ceildiv(nrows, block_size)`,
while it must be `ceildiv(nrows + 1, block_size)`. As a consequence, we
had uninitialized values in `offset_iterator[nrows]` for the case when
`nrows % block_size == 0`.

Fixes #21162

* Reduce nrows in test case to 256, don't need 768
2026-03-30 16:20:00 +02:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include llama: fix llama-model-saver (#20503) 2026-03-25 12:53:16 +02:00
src CUDA : Fix CUB's argsort when nrows % block_size == 0 CCCL < 3.1 (#21181) 2026-03-30 16:20:00 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : bump version to 0.9.8 (ggml/1442) 2026-03-18 15:17:28 +02:00