Skip to content

cuda : fix "V is K view" check for non-unified KV cache #19145

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
ggerganov merged 1 commit into from
Jan 28, 2026
Merged

cuda : fix "V is K view" check for non-unified KV cache #19145

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1295,9 +1295,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("LLAMA_ARG_CACHE_RAM").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"-kvu", "--kv-unified"},
{"-no-kvu", "--no-kv-unified"},
"use single unified KV buffer shared across all sequences (default: enabled if number of slots is auto)",
[](common_params & params) {
params.kv_unified = true;
[](common_params & params, bool value) {
params.kv_unified = value;
}
).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_PERPLEXITY, LLAMA_EXAMPLE_BATCHED}));
add_opt(common_arg(
Expand Down
2 changes: 1 addition & 1 deletion ggml/src/ggml-cuda/fattn-common.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -789,7 +789,7 @@ void launch_fattn(
const ggml_tensor * K = dst->src[1];
const ggml_tensor * V = dst->src[2];

const bool V_is_K_view = V->view_src && V->view_offs == 0 && (V->view_src == K || V->view_src == K->view_src);
const bool V_is_K_view = V->view_src && (V->view_src == K || (V->view_src == K->view_src && V->view_offs == K->view_offs));

const ggml_tensor * mask = dst->src[3];
const ggml_tensor * sinks = dst->src[4];
Expand Down
2 changes: 1 addition & 1 deletion ggml/src/ggml-cuda/fattn.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,7 +302,7 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
}
}

const bool V_is_K_view = V->view_src && V->view_offs == 0 && (V->view_src == K || V->view_src == K->view_src);
const bool V_is_K_view = V->view_src && (V->view_src == K || (V->view_src == K->view_src && V->view_offs == K->view_offs));

const int cc = ggml_cuda_info().devices[device].cc;

Expand Down
Loading