Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

need to fix cuda compile. Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/python-type-check.yml
#	examples/speculative-simple/README.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-cuda/im2col.cu
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-12 20:47:07 +08:00
parent 286e62267e fde69a3607
commit f7923b261f
43 changed files with 4544 additions and 1874 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+22 -5
View File
@@ -2485,11 +2485,29 @@ public:
}
if (need_alloc) {
mbuf_cur = std::move(mbuf);
if (!mbuf_cur.buf || mbuf_cur.total_size != mbuf.total_size) {
mbuf_cur = std::move(mbuf);
mbuf_cur.buf.reset(ggml_backend_alloc_ctx_tensors_from_buft(mbuf_cur.ctx.get(), buft));
mbuf_cur.buf.reset(ggml_backend_alloc_ctx_tensors_from_buft(mbuf_cur.ctx.get(), buft));
LLAMA_LOG_INFO("%s: allocated '%s' buffer %.3f MiB\n", __func__, ggml_backend_buft_name(buft), mbuf.total_size/1024.0/1024.0);
LLAMA_LOG_INFO("%s: allocated '%s' buffer %.3f MiB\n", __func__, ggml_backend_buft_name(buft), mbuf.total_size/1024.0/1024.0);
} else {
//LLAMA_LOG_INFO("%s: reallocating tensors in '%s' buffer %.3f MiB\n", __func__, ggml_backend_buft_name(buft), mbuf.total_size/1024.0/1024.0);
// save the old buffer and allocate the new tensors in it
auto buf = std::move(mbuf_cur.buf);
mbuf_cur = std::move(mbuf);
ggml_tallocr talloc = ggml_tallocr_new(buf.get());
for (size_t i = 0; i < mbuf_cur.org.size(); ++i) {
ggml_backend_view_init(mbuf_cur.org[i]);
ggml_tallocr_alloc(&talloc, mbuf_cur.cpy[i]);
}
mbuf_cur.buf = std::move(buf);
}
}
for (size_t i = 0; i < mbuf_cur.org.size(); ++i) {
@@ -2569,8 +2587,7 @@ public:
mbuf.org.push_back(ggml_view_1d(mbuf.ctx.get(), rinfo.tensor, n, rinfo.offset));
auto & view = mbuf.org.back();
view->buffer = rinfo.tensor->buffer;
ggml_backend_view_init(mbuf.org.back());
}
for (auto & [buft, mbuf] : mbufs_new) {