Frosty40andClaude Fable 5
efb3036c18
* sycl: add fused top-k MoE * sycl: address review: GGML_SYCL_ENABLE_FUSION env, move fusion dispatch to topk-moe * sycl: print GGML_SYCL_ENABLE_FUSION at startup like other env vars Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
13 lines
479 B
C++
13 lines
479 B
C++
#ifndef GGML_SYCL_TOPK_MOE_HPP
|
|
#define GGML_SYCL_TOPK_MOE_HPP
|
|
|
|
#include "common.hpp"
|
|
|
|
// Detect a fusable op subgraph starting at cgraph node `i` and, if found, dispatch the fused
|
|
// kernel. Returns the number of *following* nodes consumed (0 = no fusion applies at i).
|
|
int ggml_sycl_fuse(ggml_backend_sycl_context & ctx, ggml_cgraph * cgraph, int i);
|
|
|
|
int ggml_sycl_fuse_topk_moe(ggml_backend_sycl_context & ctx, ggml_cgraph * cgraph, int i);
|
|
|
|
#endif // GGML_SYCL_TOPK_MOE_HPP
|