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:
#	README.md
#	docs/build.md
#	docs/development/HOWTO-add-model.md
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
This commit is contained in:
Concedo 2025-01-10 17:57:38 +08:00
commit b154bd3671
50 changed files with 189817 additions and 187510 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file

@ -2285,6 +2285,7 @@ static vk_device ggml_vk_get_device(size_t idx) {
if (device->subgroup_size_control) {
device->subgroup_min_size = subgroup_size_control_props.minSubgroupSize;
device->subgroup_max_size = subgroup_size_control_props.maxSubgroupSize;
device_extensions.push_back("VK_EXT_subgroup_size_control");
}
device->subgroup_size_control = device->subgroup_size_control &&
@ -2293,7 +2294,6 @@ static vk_device ggml_vk_get_device(size_t idx) {
if (device->subgroup_size_control) {
device->subgroup_require_full_support = subgroup_size_control_features.computeFullSubgroups;
device_extensions.push_back("VK_EXT_subgroup_size_control");
}
#if defined(VK_KHR_cooperative_matrix)
@ -5641,9 +5641,9 @@ static void ggml_vk_op_f32_rwkv6(ggml_backend_vk_context * ctx, vk_context& subc
}
static void ggml_vk_rwkv_wkv6(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst, bool dryrun = false) {
const size_t seq_length = dst->src[0]->ne[3];
const size_t seq_length = dst->src[0]->ne[2];
const size_t n_embed = dst->ne[0];
const size_t n_heads = dst->src[0]->ne[2];
const size_t n_heads = dst->src[0]->ne[1];
const size_t n_seqs = dst->src[5]->ne[1];
ggml_vk_op_f32_rwkv6(