Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-06 04:51:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/ai-issues.yml
#	CONTRIBUTING.md
#	docs/autoparser.md
#	docs/ops.md
#	docs/ops/Metal.csv
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/hex-dma.h
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp_iface.idl
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hip/CMakeLists.txt
#	models/templates/Apriel-1.6-15b-Thinker-fixed.jinja
#	models/templates/deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja
#	models/templates/deepseek-ai-DeepSeek-V3.1.jinja
#	models/templates/llama-cpp-deepseek-r1.jinja
#	models/templates/meetkai-functionary-medium-v3.1.jinja
#	scripts/fetch_server_test_models.py
#	scripts/snapdragon/adb/run-cli.sh
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-mtmd.sh
#	scripts/snapdragon/adb/run-tool.sh
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat-peg-parser.cpp
#	tests/test-chat.cpp
#	tools/cli/cli.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-03-21 12:06:01 +08:00
parent 98f099aecc b1c70e2e54
commit 6054bacadd
33 changed files with 834 additions and 491 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+1
View File
@@ -1948,6 +1948,7 @@ uint32_t llama_context::output_reserve(int32_t n_outputs) {
LLAMA_LOG_ERROR("%s: failed to allocate output buffer of size %.2f MiB\n", __func__, new_size / (1024.0 * 1024.0));
return 0;
}
ggml_backend_buffer_clear(buf_output.get(), 0);
}
float * output_base = (float *) ggml_backend_buffer_get_base(buf_output.get());
src/llama-model.cpp
+6 -1
View File
@@ -1787,6 +1787,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
// NextN/MTP parameters (GLM-OCR)
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false);
GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
// TODO: when MTP is implemented, this should probably be updated if needed
hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
@@ -1820,6 +1821,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
// NextN/MTP parameters
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false);
GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
// TODO: when MTP is implemented, this should probably be updated if needed
hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
@@ -1866,6 +1868,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
// NextN/MTP parameters
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false);
GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
// TODO: when MTP is implemented, this should probably be updated if needed
hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
@@ -2040,6 +2043,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead, false);
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false);
GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
switch (hparams.n_layer) {
case 32: type = LLM_TYPE_30B_A3B; break;
@@ -2168,7 +2172,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
switch (hparams.n_embd) {
case 768: type = LLM_TYPE_350M; break;
case 1536: type = (hparams.n_embd == 2048 ? LLM_TYPE_7B_A1B : LLM_TYPE_1B); break;
case 1536: type = (hparams.n_ff() == 512 ? LLM_TYPE_7B_A1B : LLM_TYPE_1B); break;
case 2048: case 2560: type = LLM_TYPE_3B; break;
case 4096: type = LLM_TYPE_32B; break;
default: type = LLM_TYPE_UNKNOWN;
@@ -2222,6 +2226,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false);
ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func);
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false);
GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
// TODO: when MTP is implemented, this should probably be updated if needed
hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;