Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/020-enhancement.yml
#	.github/ISSUE_TEMPLATE/030-research.yml
#	.github/ISSUE_TEMPLATE/040-refactor.yml
#	.github/workflows/build.yml
#	Makefile
#	common/CMakeLists.txt
#	examples/CMakeLists.txt
#	examples/infill/infill.cpp
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup-stats.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	examples/retrieval/retrieval.cpp
#	examples/save-load-state/save-load-state.cpp
#	examples/speculative/speculative.cpp
#	flake.lock
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/kernels/CMakeLists.txt
#	ggml/src/ggml-cann/kernels/dup.cpp
#	ggml/src/ggml-cann/kernels/get_row_f16.cpp
#	ggml/src/ggml-cann/kernels/get_row_f32.cpp
#	ggml/src/ggml-cann/kernels/get_row_q4_0.cpp
#	tests/test-arg-parser.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2024-11-25 16:26:08 +08:00
parent a7f161da95 d9d54e498d
commit 83350ec314
21 changed files with 801 additions and 377 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama.cpp
+7 -7
View File
@@ -7223,12 +7223,12 @@ static bool weight_buft_supported(const llama_hparams & hparams, ggml_tensor * w
} break;
case GGML_OP_ADD:
{
ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, w->ne[0], 512);
ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
op_tensor = ggml_add(ctx, a, w);
} break;
case GGML_OP_MUL:
{
ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, w->ne[0], 512);
ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
op_tensor = ggml_mul(ctx, a, w);
} break;
case GGML_OP_DIV:
@@ -18375,13 +18375,13 @@ static void llama_kv_cache_defrag_internal(struct llama_context & lctx) {
static void llama_kv_cache_update_internal(struct llama_context & lctx) {
bool need_reserve = false;
// apply K-shift if needed
if (lctx.model.hparams.rope_type != LLAMA_ROPE_TYPE_NONE && lctx.kv_self.has_shift) {
if (lctx.kv_self.has_shift) {
if (!llama_kv_cache_can_shift(&lctx)) {
GGML_ABORT("Deepseek2 does not support K-shift");
GGML_ABORT("The current context does not support K-shift");
}
{
// apply K-shift if needed
if (lctx.model.hparams.rope_type != LLAMA_ROPE_TYPE_NONE) {
ggml_backend_sched_reset(lctx.sched.get());
ggml_cgraph * gf = llama_build_graph_k_shift(lctx);
@@ -20631,7 +20631,7 @@ void llama_kv_cache_update(struct llama_context * ctx) {
}
bool llama_kv_cache_can_shift(struct llama_context * ctx) {
return ctx->model.arch != LLM_ARCH_DEEPSEEK2; // not supported due to MLA
return !ctx->kv_self.recurrent && ctx->model.arch != LLM_ARCH_DEEPSEEK2; // not supported due to MLA
}
// deprecated