Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-13 02:10:39 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/release.yml
#	AGENTS.md
#	common/CMakeLists.txt
#	docs/development/parsing.md
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	tests/test-arg-parser.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grammar-llguidance.cpp
#	tests/test-tokenizer-0.cpp
#	tests/test-tokenizer-1-bpe.cpp
#	tests/test-tokenizer-1-spm.cpp
#	tools/batched-bench/batched-bench.cpp
#	tools/cli/cli.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2025-12-24 23:42:28 +08:00
parent 26d89bf589 6ce863c803
commit d1983959d2
33 changed files with 1136 additions and 485 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+15 -16
View File
@@ -469,23 +469,22 @@ llama_context::llama_context(
}
llama_context::~llama_context() {
// FIXME this currently results in a use-after-free bug if the model is freed before the context
// if (!model.hparams.no_alloc) {
// for (size_t i = 0; i < backend_ptrs.size(); ++i) {
// ggml_backend_t backend = backend_ptrs[i];
// ggml_backend_buffer_type_t buft = backend_buft[i];
if (!model.hparams.no_alloc) {
for (size_t i = 0; i < backend_ptrs.size(); ++i) {
ggml_backend_t backend = backend_ptrs[i];
ggml_backend_buffer_type_t buft = backend_buft[i];
// const size_t size_exp = backend_buf_exp_size[i];
// const size_t size_act = ggml_backend_sched_get_buffer_size(sched.get(), backend);
// if (size_exp == size_act) {
// LLAMA_LOG_DEBUG("%s: %10s compute buffer size is %8.4f MiB, matches expectation of %8.4f MiB\n",
// __func__, ggml_backend_buft_name(buft), size_act / (1024.0*1024.0), size_exp / (1024.0*1024.0));
// } else {
// LLAMA_LOG_WARN("%s: %10s compute buffer size of %8.4f MiB, does not match expectation of %8.4f MiB\n",
// __func__, ggml_backend_buft_name(buft), size_act / (1024.0*1024.0), size_exp / (1024.0*1024.0));
// }
// }
// }
const size_t size_exp = backend_buf_exp_size[i];
const size_t size_act = ggml_backend_sched_get_buffer_size(sched.get(), backend);
if (size_exp == size_act) {
LLAMA_LOG_DEBUG("%s: %10s compute buffer size is %8.4f MiB, matches expectation of %8.4f MiB\n",
__func__, ggml_backend_buft_name(buft), size_act / (1024.0*1024.0), size_exp / (1024.0*1024.0));
} else {
LLAMA_LOG_WARN("%s: %10s compute buffer size of %8.4f MiB, does not match expectation of %8.4f MiB\n",
__func__, ggml_backend_buft_name(buft), size_act / (1024.0*1024.0), size_exp / (1024.0*1024.0));
}
}
}
ggml_opt_free(opt_ctx);
}