Skip to content

llama : fix on-device state copy sizes for quantized KV caches #30541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
am17an merged 3 commits into from
Nov 5, 2026
Merged

llama : fix on-device state copy sizes for quantized KV caches #30541

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0e3dbf0
llama : fix on-device state copy sizes for quantized KV caches
wanghqc Oct 13, 2026
429ffaf
llama : drop the one-line comments
wanghqc Nov 3, 2026
bd1c3d3
llama : drop the redundant cast in the state copy size
wanghqc Nov 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions src/llama-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3090,7 +3090,8 @@ class llama_io_write_device : public llama_io_write_i {
for (const auto & winfo : winfos) {
auto * buft = ggml_backend_buffer_get_type(winfo.tensor->buffer);

const int64_t n = winfo.size/ggml_element_size(winfo.tensor);
GGML_ASSERT(winfo.size % ggml_type_size(winfo.tensor->type) == 0);
const int64_t n = winfo.size/ggml_type_size(winfo.tensor->type)*ggml_blck_size(winfo.tensor->type);

auto & mbuf = mbufs_new[buft];

Expand Down Expand Up @@ -3221,7 +3222,8 @@ class llama_io_read_device : public llama_io_read_i {
for (const auto & rinfo : rinfos) {
auto * buft = ggml_backend_buffer_get_type(rinfo.tensor->buffer);

const int64_t n = rinfo.size/ggml_element_size(rinfo.tensor);
GGML_ASSERT(rinfo.size % ggml_type_size(rinfo.tensor->type) == 0);
const int64_t n = rinfo.size/ggml_type_size(rinfo.tensor->type)*ggml_blck_size(rinfo.tensor->type);

auto & mbuf = mbufs_new[buft];

Expand Down Expand Up @@ -3288,8 +3290,8 @@ class llama_io_read_device : public llama_io_read_i {

const size_t n_copy = std::min(src_size - src_off, dst_size - dst_off);

const size_t el = ggml_element_size(src_t);
const int64_t n_el = (int64_t) (n_copy / el);
GGML_ASSERT(n_copy % ggml_type_size(src_t->type) == 0);
const int64_t n_el = n_copy / ggml_type_size(src_t->type) * ggml_blck_size(src_t->type);

auto * src_v = ggml_view_1d(ctx_scratch, src_t, n_el, src_off);
ggml_backend_view_init(src_v);
Expand Down