Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-09 14:29:15 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/server.yml
#	CMakeLists.txt
#	cmake/common.cmake
#	ggml/src/ggml-virtgpu/apir_cs_ggml-rpc-front.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-backend.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-buffer-type.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-buffer.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-device.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched.gen.h
#	ggml/src/ggml-virtgpu/backend/backend-dispatched.h
#	ggml/src/ggml-virtgpu/backend/backend.cpp
#	ggml/src/ggml-virtgpu/backend/shared/apir_cs.h
#	ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h
#	ggml/src/ggml-virtgpu/ggml-backend-buffer-type.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-device.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-reg.cpp
#	ggml/src/ggml-virtgpu/ggml-remoting.h
#	ggml/src/ggml-virtgpu/ggmlremoting_functions.yaml
#	ggml/src/ggml-virtgpu/regenerate_remoting.py
#	ggml/src/ggml-virtgpu/virtgpu-forward-backend.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-buffer-type.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-buffer.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-device.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-impl.h
#	ggml/src/ggml-virtgpu/virtgpu-forward.gen.h
#	ggml/src/ggml-virtgpu/virtgpu-shm.cpp
#	ggml/src/ggml-virtgpu/virtgpu.cpp
#	ggml/src/ggml-virtgpu/virtgpu.h
This commit is contained in:
Concedo
2026-02-04 16:21:06 +08:00
parent d9ac52a01a 25f40ca65f
commit 1f803ae27b
22 changed files with 561 additions and 316 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/completion/completion.cpp
+5 -8
View File
@@ -675,15 +675,12 @@ int main(int argc, char ** argv) {
}
}
for (int i = 0; i < (int) embd.size(); i += params.n_batch) {
int n_eval = (int) embd.size() - i;
if (n_eval > params.n_batch) {
n_eval = params.n_batch;
}
if (!embd.empty()) {
int n_eval = (int) embd.size();
LOG_DBG("eval: %s\n", string_from(ctx, embd).c_str());
if (llama_decode(ctx, llama_batch_get_one(&embd[i], n_eval))) {
GGML_ASSERT(n_eval <= params.n_batch);
if (llama_decode(ctx, llama_batch_get_one(embd.data(), n_eval))) {
LOG_ERR("%s : failed to eval\n", __func__);
return 1;
}
@@ -744,7 +741,7 @@ int main(int argc, char ** argv) {
common_sampler_accept(smpl, embd_inp[n_consumed], /* accept_grammar= */ false);
++n_consumed;
if ((int) embd.size() >= params.n_batch) {
if ((int) embd.size() == params.n_batch) {
break;
}
}