vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 02:49:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge commit '8f47e25f56' into concedo_experimental

Browse source 
# Conflicts:
#	.github/labeler.yml
#	.github/workflows/build-linux-cross.yml
#	docs/backend/CANN.md
#	examples/batched.swift/Sources/main.swift
#	examples/embedding/embedding.cpp
#	examples/gritlm/gritlm.cpp
#	examples/llama.android/llama/src/main/cpp/llama-android.cpp
#	examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	examples/passkey/passkey.cpp
#	examples/retrieval/retrieval.cpp
#	examples/save-load-state/save-load-state.cpp
#	examples/simple-chat/simple-chat.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	tools/batched-bench/batched-bench.cpp
#	tools/cvector-generator/cvector-generator.cpp
#	tools/imatrix/imatrix.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/perplexity/perplexity.cpp
#	tools/run/run.cpp
This commit is contained in:
Concedo 2025-06-13 22:05:03 +08:00
commit 4204f111f7
24 changed files with 204 additions and 91 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -942,7 +942,7 @@ struct common_init_result common_init_from_params(common_params & params) {
return iparams;
}
if (params.ctx_shift && !llama_kv_self_can_shift(lctx)) {
if (params.ctx_shift && !llama_memory_can_shift(llama_get_memory(lctx))) {
LOG_WRN("%s: KV cache shifting is not supported for this context, disabling KV cache shifting\n", __func__);
params.ctx_shift = false;
}
@ -1049,7 +1049,7 @@ struct common_init_result common_init_from_params(common_params & params) {
if (llama_model_has_decoder(model)) {
llama_decode(lctx, llama_batch_get_one(tmp.data(), std::min(tmp.size(), (size_t) params.n_batch)));
}
llama_kv_self_clear(lctx);
llama_memory_clear(llama_get_memory(lctx), true);
llama_synchronize(lctx);
llama_perf_context_reset(lctx);
llama_set_warmup(lctx, false);