Skip to content

UPSTREAM PR #17514: vulkan: use a fixed 1KB buffer for the add_rms_fusion opt #332

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

UPSTREAM PR #17514: vulkan: use a fixed 1KB buffer for the add_rms_fusion opt #332

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
4 changes: 2 additions & 2 deletions ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5256,7 +5256,8 @@ static void ggml_vk_init(ggml_backend_vk_context * ctx, size_t idx) {
ctx->prealloc_size_x = 0;
ctx->prealloc_size_y = 0;
ctx->prealloc_size_split_k = 0;
ctx->prealloc_size_add_rms_partials = 0;
// Fixed size of 1KB, for deterministic behavior
ctx->prealloc_size_add_rms_partials = 1024;

ctx->fence = ctx->device->device.createFence({});
ctx->almost_ready_fence = ctx->device->device.createFence({});
Expand Down Expand Up @@ -12945,7 +12946,6 @@ static ggml_status ggml_backend_vk_graph_compute(ggml_backend_t backend, ggml_cg
ctx->fused_ops_write_mask = 0;
}

ctx->prealloc_size_add_rms_partials = std::max(ctx->prealloc_size_add_rms_partials, ctx->prealloc_size_add_rms_partials_offset);
ctx->last_total_mul_mat_bytes = total_mul_mat_bytes;

if (vk_perf_logger_enabled) {
Expand Down