wylab/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-14 18:02:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

sycl : fix oneDNN scratchpad breaking the pool free order (#28704)

Browse Source
This commit is contained in:
Łukasz Ślusarczyk
2026-09-14 02:24:06 -04:00
committed by GitHub
parent 093a2f86c3
commit 661643e430
2 changed files with 4 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/common.hpp
-19
View File
@@ -401,29 +401,10 @@ struct ggml_backend_sycl_context {
dnnl::stream stream_dnnl() {
return stream_dnnl(device, 0);
}
dnnl::memory get_scratchpad_mem(const dnnl::memory::desc & scratchpad_md,
const dnnl::engine & eng, const queue_ptr q) {
ggml_sycl_pool_alloc<uint8_t> * pool;
auto it = scratchpad_map.find(q);
if (it == scratchpad_map.end()) {
scratchpad_map[q] = std::make_unique<ggml_sycl_pool_alloc<uint8_t>>(this->pool());
pool = scratchpad_map[q].get();
} else {
pool = it->second.get();
}
size_t scratchpad_size = scratchpad_md.get_size();
if (scratchpad_size > pool->actual_size) {
pool->realloc(scratchpad_size);
}
void * mem_ptr = pool->get();
return dnnl::memory(scratchpad_md, eng, mem_ptr);
}
#endif
// pool
std::unique_ptr<ggml_sycl_pool> pools[GGML_SYCL_MAX_DEVICES];
std::unordered_map<sycl::queue *, std::unique_ptr<ggml_sycl_pool_alloc<uint8_t>>> scratchpad_map;
std::unique_ptr<ggml_sycl_fattn_kv_buffers> fattn_bufs[GGML_SYCL_MAX_DEVICES];
ggml/src/ggml-sycl/gemm.hpp
+4 -2
View File
@@ -66,8 +66,10 @@ public:
auto matmul_pd = dnnl::matmul::primitive_desc(eng, a_in_md, b_in_md, c_md, primitive_attr);
auto c_mem = dnnl::memory(matmul_pd.dst_desc(), eng, c);
auto scratchpad_md = matmul_pd.scratchpad_desc();
auto scratchpad_mem = ctx.get_scratchpad_mem(scratchpad_md, eng, q);
const auto scratchpad_md = matmul_pd.scratchpad_desc();
ggml_sycl_pool_alloc<uint8_t> scratchpad(ctx.pool());
void * scratchpad_ptr = scratchpad_md.get_size() > 0 ? scratchpad.alloc(scratchpad_md.get_size()) : nullptr;
auto scratchpad_mem = dnnl::memory(scratchpad_md, eng, scratchpad_ptr);
auto matmul_prim = dnnl::matmul(matmul_pd);