tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-06 01:05:03 -04:00
Code Issues Packages Projects Releases Wiki Activity

SYCL: Refactor ggml_sycl_compute_forward (#11121)

Browse Source 
* SYCL: refactor ggml_sycl_compute_forward

* SYCL: add back GGML_USED(dst) to ggml_sycl_cpy

* SYCL: add function name to noop debug

* SYCL: Some device info print refactoring and add details of XMX availability
This commit is contained in:
Akarshan Biswas
2025-01-10 05:43:03 +05:30
committed by GitHub
parent 1204f97270
commit c6860cc734
15 changed files with 223 additions and 230 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
ggml/src/ggml-sycl/element_wise.hpp
View File

@@ -25,52 +25,52 @@ static __dpct_inline__ float op_div(const float a, const float b) {
}
void ggml_sycl_sqrt(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_sqrt(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_sin(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_sin(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_cos(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_cos(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_acc(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_acc(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_gelu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_gelu(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_silu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_silu(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_gelu_quick(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_gelu_quick(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_tanh(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_tanh(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_relu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_relu(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_sigmoid(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_sigmoid(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_hardsigmoid(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_hardsigmoid(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_hardswish(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_hardswish(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_exp(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_exp(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_log(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_log(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_neg(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_neg(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_step(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_step(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_leaky_relu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_leaky_relu(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_sqr(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_sqr(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_upscale(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_upscale(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_pad(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_pad(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_add(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_add(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_sub(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_sub(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_mul(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_mul(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_div(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
void ggml_sycl_div(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
#endif // GGML_SYCL_ELEMENTWISE_HPP