tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-07 17:53:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: Split large mul_mat_id to fit in shared memory (#14451)

Browse Source
This commit is contained in:
Jeff Bolz
2025-07-01 03:43:08 -05:00
committed by GitHub
parent eff5e45443
commit 6a746cf9c4
2 changed files with 38 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@ -5966,7 +5966,30 @@ static void ggml_vk_mul_mat_id(ggml_backend_vk_context * ctx, vk_context& subctx
if (src2->ne[1] == 1 && (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16 || ggml_is_quantized(src0->type))) {
ggml_vk_mul_mat_vec_id_q_f16(ctx, subctx, src0, src1, src2, dst, dryrun);
} else {
ggml_vk_mul_mat_id_q_f16(ctx, subctx, src0, src1, src2, dst, dryrun);
// Split based on number of ids, to fit in shared memory
const uint32_t nei0 = (uint32_t)src2->ne[0];
const uint32_t nei1 = (uint32_t)src2->ne[1];
GGML_ASSERT(nei0 <= 4096);
const uint32_t split_size = std::min(nei1, 4096u / nei0);
ggml_tensor src1_copy = *src1;
ggml_tensor src2_copy = *src2;
ggml_tensor dst_copy = *dst;
for (uint32_t token_start = 0; token_start < nei1; token_start += split_size) {
const uint32_t n_tokens = std::min(split_size, nei1 - token_start);
src1_copy.view_offs = src1->view_offs + token_start * src1_copy.nb[2];
src2_copy.view_offs = src2->view_offs + token_start * src2_copy.nb[1];
dst_copy.view_offs = dst->view_offs + token_start * dst_copy.nb[2];
src1_copy.ne[2] = n_tokens;
src2_copy.ne[1] = n_tokens;
dst_copy.ne[2] = n_tokens;
ggml_vk_mul_mat_id_q_f16(ctx, subctx, src0, &src1_copy, &src2_copy, &dst_copy, dryrun);
}
}
}
@ -10135,10 +10158,16 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
ggml_type src0_type = op->src[0]->type;
ggml_backend_vk_device_context * ctx = (ggml_backend_vk_device_context *)dev->context;
const vk_device& device = ggml_vk_get_device(ctx->device);
if (op->op == GGML_OP_MUL_MAT_ID && !device->mul_mat_id_s[src0_type] && !device->mul_mat_id_m[src0_type] && !device->mul_mat_id_l[src0_type]) {
if (op->op == GGML_OP_MUL_MAT_ID) {
if (!device->mul_mat_id_s[src0_type] && !device->mul_mat_id_m[src0_type] && !device->mul_mat_id_l[src0_type]) {
// If there's not enough shared memory for row_ids and the result tile, fallback to CPU
return false;
}
// Check against size of shared memory variable
if (op->src[2]->ne[0] > 4096) {
return false;
}
}
switch (src0_type) {
case GGML_TYPE_F32:
case GGML_TYPE_F16:

5
tests/test-backend-ops.cpp
View File

@ -4623,6 +4623,11 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
// this case is verified (pass) in Intel(R) Data Center GPU Max 1100 (sycl backend) and NV A30 (cuda backend)
// test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F16, 512, 262144, 9216, {1, 1}, {1, 1}));
// test large experts*tokens
for (bool b : {false, true}) {
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 16, 16, b, 32, 1024, 16));
}
for (ggml_type type_a : base_types) {
for (ggml_type type_b : {GGML_TYPE_F32 /*, GGML_TYPE_F16 */}) {
for (int n_mats : {4, 8}) {