Markus Fritsche
107ccddbb1
Final deliverables (mesa-panvk-shared-tls-wls + llama.cpp-mali-mmq-warptile) at top of patches/; iteration trail moved to patches/iterations/. Public-facing README with the 4.8x result and the two-fix summary. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
30 lines
1.6 KiB
Diff
30 lines
1.6 KiB
Diff
diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
|
|
index 0a79310..8732cf9 100644
|
|
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
|
|
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
|
|
@@ -14684,11 +14684,14 @@ static ggml_status ggml_backend_vk_graph_compute(ggml_backend_t backend, ggml_cg
|
|
// (and scaled down based on model size, so smaller models submit earlier).
|
|
// Also submit at least every 100 nodes, in case there are workloads without as much matmul.
|
|
int nodes_per_submit = 100;
|
|
+ if (const char* e = getenv("GGML_VK_NODES_PER_SUBMIT")) { nodes_per_submit = atoi(e); }
|
|
int submitted_nodes = 0;
|
|
int submit_count = 0;
|
|
uint64_t mul_mat_bytes = 0;
|
|
uint64_t total_mul_mat_bytes = 0;
|
|
- uint64_t mul_mat_bytes_per_submit = std::min(uint64_t(100*1000*1000), ctx->last_total_mul_mat_bytes / 40u);
|
|
+ uint64_t mul_mat_bytes_cap = 100*1000*1000;
|
|
+ if (const char* e = getenv("GGML_VK_MAX_MUL_MAT_BYTES_PER_SUBMIT")) { mul_mat_bytes_cap = strtoull(e, nullptr, 10); }
|
|
+ uint64_t mul_mat_bytes_per_submit = std::min(mul_mat_bytes_cap, ctx->last_total_mul_mat_bytes / 40u);
|
|
for (int i = 0; i < cgraph->n_nodes; i++) {
|
|
if (first_node_in_batch) {
|
|
submit_node_idx = i;
|
|
@@ -14925,7 +14928,7 @@ static ggml_status ggml_backend_vk_graph_compute(ggml_backend_t backend, ggml_cg
|
|
submitted_nodes = 0;
|
|
mul_mat_bytes = 0;
|
|
if (submit_count < 3) {
|
|
- mul_mat_bytes_per_submit *= 2;
|
|
+ mul_mat_bytes_per_submit = std::min(mul_mat_bytes_per_submit * 2, mul_mat_bytes_cap);
|
|
}
|
|
submit_count++;
|
|
}
|