Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/labeler.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/server.yml
#	.github/workflows/ui-build.yml
#	.github/workflows/ui-ci.yml
#	.github/workflows/ui-publish.yml
#	.gitignore
#	CMakeLists.txt
#	CODEOWNERS
#	scripts/ui-download.cmake
#	scripts/xxd.cmake
#	tests/test-backend-ops.cpp
#	tests/test-reasoning-budget.cpp
#	tools/CMakeLists.txt
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-16 22:56:33 +08:00
parent 3095da076a 366c5e2a3b
commit 9203b6a051
745 changed files with 17016 additions and 14593 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+14 -1
View File
@@ -1525,10 +1525,23 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) {
layer.ssm_beta_in_s = create_tensor(tn(LLM_TENSOR_SSM_BETA, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
}
// output scales
if (output && output->type == GGML_TYPE_NVFP4) {
// weight scale
if (!output_s) {
output_s = create_tensor(tn(LLM_TENSOR_OUTPUT, "scale"), {1}, TENSOR_NOT_REQUIRED);
}
// input scale
if (!output_in_s) {
output_in_s = create_tensor(tn(LLM_TENSOR_OUTPUT, "input_scale"), {1}, TENSOR_NOT_REQUIRED);
}
}
}
ml.done_getting_tensors();
GGML_ASSERT(!(output && tok_embd &&
strcmp(output->name, tok_embd->name) == 0 &&
output->type == GGML_TYPE_NVFP4));
// populate tensors_by_name
for (auto & [_, ctx_ptr] : ml.ctx_map) {
for (auto * cur = ggml_get_first_tensor(ctx_ptr.get()); cur != NULL; cur = ggml_get_next_tensor(ctx_ptr.get(), cur)) {