vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 01:54:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/intel.Dockerfile
#	CMakeLists.txt
#	README.md
#	common/CMakeLists.txt
#	docs/multimodal.md
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/gemm.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	src/llama-context.cpp
This commit is contained in:
Concedo 2025-06-14 09:05:45 +08:00
commit 5f9e96e82d
18 changed files with 505 additions and 247 deletions
Download patch file Download diff file Expand all files Collapse all files

7
tools/server/server.cpp
View file

@ -2017,11 +2017,6 @@ struct server_context {
params_base.n_cache_reuse = 0;
SRV_WRN("%s\n", "cache_reuse is not supported by this context, it will be disabled");
}
if (!params_base.speculative.model.path.empty()) {
SRV_ERR("%s\n", "err: speculative decode is not supported by this context");
return false;
}
}
return true;
@ -3222,7 +3217,7 @@ struct server_context {
}
const auto n_swa = llama_model_n_swa(model);
if (pos_min > slot.n_past - n_swa) {
if (pos_min > std::max(0, slot.n_past - n_swa)) {
SLT_WRN(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d, n_swa = %d\n", slot.n_past, (int) slot.cache_tokens.size(), slot.id, pos_min, n_swa);
SLT_WRN(slot, "forcing full prompt re-processing due to lack of cache data (likely due to SWA, see %s)\n",
"https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055");