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:
#	docs/backend/CANN.md
#	docs/multimodal/minicpmo2.6.md
#	docs/multimodal/minicpmv2.5.md
#	docs/multimodal/minicpmv2.6.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/repack.cpp
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/add.cl
#	ggml/src/ggml-opencl/kernels/mul.cl
#	scripts/compare-commits.sh
#	scripts/compare-llama-bench.py
#	scripts/sync-ggml.last
#	tools/server/README.md
This commit is contained in:
Concedo
2025-08-02 10:25:10 +08:00
parent b04362f831 9c35706b98
commit f430916a71
57 changed files with 6028 additions and 731 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+10 -1
View File
@@ -113,6 +113,15 @@ llama_context::llama_context(
}
}
{
const char * LLAMA_GRAPH_REUSE_DISABLE = getenv("LLAMA_GRAPH_REUSE_DISABLE");
graph_reuse_disable = LLAMA_GRAPH_REUSE_DISABLE ? (atoi(LLAMA_GRAPH_REUSE_DISABLE) != 0) : graph_reuse_disable;
if (graph_reuse_disable) {
LLAMA_LOG_WARN("%s: graph reuse disabled\n", __func__);
}
}
const uint32_t n_ctx_per_seq = cparams.n_ctx / cparams.n_seq_max;
LLAMA_LOG_INFO("%s: n_seq_max = %u\n", __func__, cparams.n_seq_max);
@@ -716,7 +725,7 @@ llm_graph_result * llama_context::process_ubatch(const llama_ubatch & ubatch, ll
// in order to correctly reuse a graph, it's full topology has to be uniquely determined by these parameters
const auto gparams = graph_params(res, ubatch, mctx, gtype);
if (res->can_reuse(gparams)) {
if (!graph_reuse_disable && res->can_reuse(gparams)) {
//LLAMA_LOG_DEBUG("%s: reusing previous graph\n", __func__);
n_reused++;