diff options
| author | AidanBeltonS <87009434+AidanBeltonS@users.noreply.github.com> | 2024-02-26 14:02:11 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-02-26 19:32:11 +0530 |
| commit | e849078c6e09e72fdd2c95ba61f5fba9a7b2d9ef (patch) | |
| tree | e7a34b8b13e10867d4194cbec4f78d111900b344 /llama.cpp | |
| parent | 67fd33132fab93e6c2087bd6fa656a8a57419efa (diff) | |
[SYCL] Add support for soft_max ALiBi (#5639)
* Add support for bias
* Update pre-processor
* rm commented code
* fix format
* fix CI
---------
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
Diffstat (limited to 'llama.cpp')
| -rw-r--r-- | llama.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
@@ -4894,8 +4894,8 @@ static struct ggml_tensor * llm_build_kqv( ggml_mul_mat_set_prec(kq, GGML_PREC_F32); } -#if defined(GGML_USE_VULKAN) || defined(GGML_USE_KOMPUTE) || defined(GGML_USE_SYCL) -#pragma message("TODO: ALiBi support in ggml_soft_max_ext is not implemented for Vulkan, Kompute, and SYCL") +#if defined(GGML_USE_VULKAN) || defined(GGML_USE_KOMPUTE) +#pragma message("TODO: ALiBi support in ggml_soft_max_ext is not implemented for Vulkan, and Kompute") #pragma message(" Falling back to ggml_alibi(). Will become an error in Mar 2024") #pragma message("ref: https://github.com/ggerganov/llama.cpp/pull/5488") if (hparams.f_max_alibi_bias > 0.0f) { |