Titaniumtown
3d93885352
Port of https://github.com/ggml-org/llama.cpp/pull/23940. Arc Pro B70, Qwen 3.6 27B Q4_K - Medium (48 of its 64 blocks run gated_delta_net), -ngl 99 -fa 1 -ctk f16 -ctv f16 -b 2048 -ub 2048, interleaved A/B passes of r=3: tg128 23.91 / 23.90 / 23.90 -> 24.19 / 24.17 / 24.20 +1.2% tg128 (rebuild) 23.81 / 23.81 -> 24.09 / 24.10 +1.2% pp2048 1050.8 / 1053.9 -> 1053.8 / 1054.5 flat 2 seqs, tg128 32.73 / 32.75 -> 33.11 / 33.10 +1.1%
20 lines
839 B
C++
20 lines
839 B
C++
#pragma once
|
|
|
|
#include <sycl/sycl.hpp>
|
|
#include "dpct/helper.hpp"
|
|
#include "common.hpp"
|
|
#include "ggml.h"
|
|
|
|
// fused-kernel recurrent-state output; strides in elements (per-seq stride is always D, set in-kernel)
|
|
struct ggml_sycl_gated_delta_net_fused_cache {
|
|
float * data; // rollback slot 0
|
|
int64_t slot_stride; // between rollback slots (0 when K==1)
|
|
};
|
|
|
|
void ggml_sycl_op_gated_delta_net(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
|
|
void ggml_sycl_gated_delta_net(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
|
|
|
|
// same op, but writes the snapshot(s) into the cache instead of dst (see ggml_sycl_try_gdn_cache_fusion)
|
|
void ggml_sycl_op_gated_delta_net_fused_cache(ggml_backend_sycl_context & ctx, ggml_tensor * dst,
|
|
ggml_sycl_gated_delta_net_fused_cache cache);
|