Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-01 10:00:51 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '6effcecd0bf3cb2209999cecfa297ed4d8523b5a' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-msys.yml
#	.pi/gg/SYSTEM.md
#	common/CMakeLists.txt
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	scripts/ui-assets.cmake
#	src/llama-model.cpp
#	tools/cli/cli.cpp
#	tools/imatrix/imatrix.cpp
#	tools/quantize/quantize.cpp
#	tools/server/README.md
#	tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo
2026-06-07 17:10:58 +08:00
parent 5f39666705 6effcecd0b
commit 202aaef40b
152 changed files with 1188 additions and 878 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+5 -5
View File
@@ -344,7 +344,7 @@ llama_context::llama_context(
// enabling pipeline parallelism in the scheduler increases memory usage, so it is only done when necessary
bool pipeline_parallel =
model.n_devices() > 1 &&
model.n_gpu_layers() > model.hparams.n_layer &&
model.n_gpu_layers() > model.hparams.n_layer() &&
model.split_mode() == LLAMA_SPLIT_MODE_LAYER &&
cparams.offload_kqv &&
!model.has_tensor_overrides();
@@ -2361,7 +2361,7 @@ llm_graph_cb llama_context::graph_get_cb() const {
// norm may be automatically assigned to the backend of the previous layer, increasing data transfer between backends
// FIXME: fix in ggml_backend_sched
const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer;
const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer();
if (ubatch.n_tokens < 32 || full_offload) {
if (il != -1 && strcmp(name, "norm") == 0) {
const auto & dev_layer = model.dev_layer(il);
@@ -3426,7 +3426,7 @@ llama_context * llama_init_from_model(
if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_k)) {
const uint32_t blck_size = ggml_blck_size(params.type_k);
for (uint32_t il = 0; il < model->hparams.n_layer; ++il) {
for (uint32_t il = 0; il < model->hparams.n_layer(); ++il) {
if (model->hparams.n_embd_head_k(il) % blck_size != 0) {
LLAMA_LOG_ERROR("%s: K cache type %s with block size %u does not divide n_embd_head_k=%u\n",
__func__, ggml_type_name(params.type_k), blck_size, model->hparams.n_embd_head_k(il));
@@ -3437,7 +3437,7 @@ llama_context * llama_init_from_model(
if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_v)) {
const uint32_t blck_size = ggml_blck_size(params.type_v);
for (uint32_t il = 0; il < model->hparams.n_layer; ++il) {
for (uint32_t il = 0; il < model->hparams.n_layer(); ++il) {
if (model->hparams.n_embd_head_v(il) % blck_size != 0) {
LLAMA_LOG_ERROR("%s: V cache type %s with block size %u does not divide n_embd_head_v=%u\n",
__func__, ggml_type_name(params.type_v), blck_size, model->hparams.n_embd_head_v(il));
@@ -3459,7 +3459,7 @@ llama_context * llama_init_from_model(
}
if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP &&
model->hparams.nextn_predict_layers == 0) {
model->hparams.n_layer_nextn == 0) {
LLAMA_LOG_WARN("%s: context type MTP requested but model doesn't contain MTP layers\n", __func__);
return nullptr;
}