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/workflows/build-ibm.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/code-style.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/fusion.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	.pi/gg/SYSTEM.md
#	CMakeLists.txt
#	ci/run.sh
#	common/CMakeLists.txt
#	docs/backend/SYCL.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/base.hpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/gemm.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mem.cpp
#	scripts/sync-ggml.last
#	src/CMakeLists.txt
#	tests/CMakeLists.txt
#	tests/snapshots/nvidia-nemotron-3-nano-30b-a3b.schema
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-llama-archs.cpp
#	tests/test-quant-type-selection.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/CMakeLists.txt
This commit is contained in:
Concedo
2026-09-14 22:44:04 +08:00
parent a4f7e70b9f 41abbfd599
commit c43b36bcb5
39 changed files with 503 additions and 1530 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+5 -6
View File
@@ -1593,6 +1593,11 @@ common_context_seq_rm_type common_context_can_seq_rm(llama_context * ctx) {
return COMMON_CONTEXT_SEQ_RM_TYPE_NO;
}
if (llama_n_rs_seq(ctx) > 0) {
COM_TRC("%s", "the context supports bounded partial sequence removal\n");
return COMMON_CONTEXT_SEQ_RM_TYPE_RS;
}
common_context_seq_rm_type res = COMMON_CONTEXT_SEQ_RM_TYPE_PART;
llama_memory_clear(mem, true);
@@ -1609,12 +1614,6 @@ common_context_seq_rm_type common_context_can_seq_rm(llama_context * ctx) {
goto done;
}
if (llama_n_rs_seq(ctx) > 0) {
COM_TRC("%s", "the context supports bounded partial sequence removal\n");
res = COMMON_CONTEXT_SEQ_RM_TYPE_RS;
goto done;
}
// try to remove the last tokens
if (!llama_memory_seq_rm(mem, 0, 1, -1)) {
COM_TRC("%s", "the context does not support partial sequence removal\n");