vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/cuda.Dockerfile
#	.devops/musa.Dockerfile
#	.github/workflows/build.yml
#	README.md
#	docs/docker.md
#	examples/imatrix/imatrix.cpp
#	examples/llama-bench/llama-bench.cpp
#	examples/main/README.md
#	examples/perplexity/perplexity.cpp
#	examples/server/README.md
#	ggml/src/ggml-cpu/ggml-cpu.c
#	ggml/src/ggml-cuda/CMakeLists.txt
#	models/templates/deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja
#	models/templates/deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja
#	scripts/get_chat_template.py
#	scripts/sync-ggml.last
#	tests/test-chat.cpp
#	tests/test-gguf.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2025-02-15 00:49:46 +08:00
commit 754fef5204
27 changed files with 1845 additions and 548 deletions
Download patch file Download diff file Expand all files Collapse all files

13
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file

@ -1434,6 +1434,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
VK_LOG_DEBUG("ggml_vk_load_shaders(" << device->name << ")");
// some shaders have a minimum subgroup size
const uint32_t subgroup_size_8 = std::max(device->subgroup_size, 8u);
const uint32_t subgroup_size_16 = std::max(device->subgroup_size, 16u);
const uint32_t subgroup_size_32 = std::max(device->subgroup_size, 32u);
@ -1496,13 +1497,13 @@ static void ggml_vk_load_shaders(vk_device& device) {
const uint32_t tk_m = device->coopmat_support ? device->coopmat_k : 1;
const uint32_t tk_s = device->coopmat_support ? device->coopmat_k : 1;
l_warptile = { 128, 128, 128, 16, device->subgroup_size * 2, 64, 2, tm_l, tn_l, tk_l, device->subgroup_size };
m_warptile = { 128, 64, 64, 16, device->subgroup_size, 32, 2, tm_m, tn_m, tk_m, device->subgroup_size };
s_warptile = { subgroup_size_16, 32, 32, 16, 32, 32, 2, tm_s, tn_s, tk_s, device->subgroup_size };
l_warptile = { 128, 128, 128, 16, subgroup_size_8 * 2, 64, 2, tm_l, tn_l, tk_l, subgroup_size_8 };
m_warptile = { 128, 64, 64, 16, subgroup_size_8, 32, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
s_warptile = { subgroup_size_16, 32, 32, 16, 32, 32, 2, tm_s, tn_s, tk_s, subgroup_size_8 };
l_warptile_mmq = { 128, 128, 128, 32, device->subgroup_size * 2, 64, 2, tm_l, tn_l, tk_l, device->subgroup_size };
m_warptile_mmq = { 128, 64, 64, 32, device->subgroup_size, 32, 2, tm_m, tn_m, tk_m, device->subgroup_size };
s_warptile_mmq = { subgroup_size_32, 32, 32, 32, 32, 32, 2, tm_s, tn_s, tk_s, device->subgroup_size };
l_warptile_mmq = { 128, 128, 128, 32, subgroup_size_8 * 2, 64, 2, tm_l, tn_l, tk_l, subgroup_size_8 };
m_warptile_mmq = { 128, 64, 64, 32, subgroup_size_8, 32, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
s_warptile_mmq = { subgroup_size_32, 32, 32, 32, 32, 32, 2, tm_s, tn_s, tk_s, subgroup_size_8 };
l_mmq_wg_denoms = l_wg_denoms = {128, 128, 1 };
m_mmq_wg_denoms = m_wg_denoms = { 64, 64, 1 };