sleepy
6ad84d543c
3-model council (GLM-5.1, Minimax-M2.7, Kimi k2p5) analyzed Intel Arc GPU performance issues and produced patches for llama.cpp: Phase 1 - SYCL Sync: Enable graph execution by default (GGML_SYCL_DISABLE_GRAPH) Phase 2 - SYCL Kernel: Fix VER_GEN12/13 thresholds, tune DMMV_X/MMV_Y Phase 3 - Vulkan Intel: Arc 140T device-ID Xe2 override Includes: - Phased apply script (apply-phase.sh [1|2|3|all]) - Master apply script with --status/--reverse/--dry-run - Per-phase READMEs with testing checklists - Council deliberation logs (gitignored in logs/) Verified: all patches apply/reverse cleanly via git apply. Static verification: VER_GEN arithmetic and DMMV_X divisibility pass.
18 lines
450 B
Diff
18 lines
450 B
Diff
diff --git a/ggml/src/ggml-sycl/presets.hpp b/ggml/src/ggml-sycl/presets.hpp
|
|
index dc4dad1..a2e4ce2 100644
|
|
--- a/ggml/src/ggml-sycl/presets.hpp
|
|
+++ b/ggml/src/ggml-sycl/presets.hpp
|
|
@@ -54,10 +54,10 @@
|
|
|
|
// dmmv = dequantize_mul_mat_vec
|
|
#ifndef GGML_SYCL_DMMV_X
|
|
-#define GGML_SYCL_DMMV_X 32
|
|
+#define GGML_SYCL_DMMV_X 64
|
|
#endif
|
|
#ifndef GGML_SYCL_MMV_Y
|
|
-#define GGML_SYCL_MMV_Y 1
|
|
+#define GGML_SYCL_MMV_Y 2
|
|
#endif
|
|
|
|
#ifndef K_QUANTS_PER_ITERATION
|