llama.cpp

0 Fork 0

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-28 17:56:13 +08:00

Files

T

Michael Taylor 7170cad4d0 sycl: fix CONV_2D wrong results for non-contiguous input (#30363 )

* sycl: fix CONV_2D wrong results for non-contiguous input

The kernel indexes the `input` as a contiguous [W, H, C, N] tensor, but
supports_op claimed the op for any layout. A non-contiguous (e.g. `CWHN`
permuted) input was read with the wrong element offsets, silently
producing wrong results.

Gate the CONV_2D op on `input` and `kernel` contiguity, matching the
CUDA backend contract, and assert input contiguity in the op.

`test-backend-ops -b SYCL0 -o CONV_2D`: goes from 16 failures to 0,
none.

```text
  2006/2006 tests passed
  Backend SYCL0: OK
Backend 2/2: CPU
  Skipping
2/2 backends passed
OK
```

Assisted-by: pi (unsloth/Qwen3.8-27B-GGUF:Q4_K_M via llama.cpp)

* sycl : CONV_2D cwhn=1 support

Make the SYCL backend compute `GGML_OP_CONV_2D` correctly for `cwhn=1` (CWHN
channel-order) inputs and kernels, so the previously failing test-
backend-ops CONV_2D cases pass on SYCL instead of being skipped or
miscomputed.

- Implement CWHN layout support in `ggml/src/ggml-sycl/conv2d.cpp`
  (`ggml_sycl_op_conv2d`).
- Update SYCL `supports_op` for `GGML_OP_CONV_2D` in
  `ggml/src/ggml-sycl/ggml-sycl.cpp` to accept both layouts.

Assisted-by: pi (Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF via llama.cpp)

* sycl docs : update ops for SYCL

2026-10-22 16:19:58 +08:00

BLAS.csv

docs(ggml): update backend ops (#18734 )

2026-01-10 18:48:17 +08:00

CANN.csv

docs : update ops.md for CANN backend (#18654 )

2026-01-16 13:32:17 +01:00

CPU.csv

docs : refresh CPU ops support matrix (#29666 )

2026-10-01 08:17:51 +03:00

CUDA.csv

cuda : add BF16 support for XIELU (#29955 )