Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-05 04:21:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/cpu.Dockerfile
#	.devops/cuda.Dockerfile
#	.devops/intel.Dockerfile
#	.devops/musa.Dockerfile
#	.devops/openvino.Dockerfile
#	.devops/rocm.Dockerfile
#	.devops/vulkan.Dockerfile
#	.devops/zendnn.Dockerfile
#	.github/workflows/build-webgpu.yml
#	.github/workflows/release.yml
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/binary.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/concat.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/scale.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-mtmd-c-api.c
#	tools/cli/cli.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-06-10 17:21:05 +08:00
parent 258ca8fd90 e25a32e98c
commit afc8de2c6b
55 changed files with 1514 additions and 185 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-graph.cpp
+13 -4
View File
@@ -567,7 +567,10 @@ void llm_graph_input_attn_kv_iswa::set_input(const llama_ubatch * ubatch) {
mctx->get_base()->set_input_v_idxs(self_v_idxs, ubatch);
}
mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn);
// the kq mask guards on its own buffer: shared cells leave idxs unbacked while the mask stays live
if (self_kq_mask && self_kq_mask->buffer) {
mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn);
}
// swa tensors may not be allocated if there are no SWA attention layers
if (self_k_idxs_swa && self_k_idxs_swa->buffer) {
@@ -575,7 +578,9 @@ void llm_graph_input_attn_kv_iswa::set_input(const llama_ubatch * ubatch) {
mctx->get_swa()->set_input_v_idxs(self_v_idxs_swa, ubatch);
}
mctx->get_swa()->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn);
if (self_kq_mask_swa && self_kq_mask_swa->buffer) {
mctx->get_swa()->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn);
}
if (self_k_rot) {
mctx->get_base()->set_input_k_rot(self_k_rot);
@@ -607,7 +612,9 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) {
//res &= self_v_idxs->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
}
res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams);
if (self_kq_mask && self_kq_mask->buffer) {
res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams);
}
// swa tensors may not be allocated if there are no SWA attention layers
if (self_k_idxs_swa && self_k_idxs_swa->buffer) {
@@ -615,7 +622,9 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) {
//res &= self_v_idxs_swa->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
}
res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams);
if (self_kq_mask_swa && self_kq_mask_swa->buffer) {
res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams);
}
return res;
}