upstream-archive/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-02 02:47:33 -05:00
Code Issues Packages Projects Releases Wiki Activity

metal : key the fa-vec tuned table by family instead of SKU (llama/29075)

Browse Source 
* key the fa-vec tuned table by family instead of SKU

* fall back to baseline for untuned fa-vec gpu families
This commit is contained in:
YiChen Lv
2026-09-23 20:46:47 +03:00
committed by Georgi Gerganov
parent 185213231b
commit 6bc51cc745
3 changed files with 1060 additions and 3945 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-ops.cpp
-1
View File
@@ -3584,7 +3584,6 @@ int ggml_metal_op_flash_attn_ext(ggml_metal_op_t ctx, int idx) {
auto cfg = use_sparse
? ggml_metal_tuning::fa_vec_baseline_cfg((int) ne00, (int) ne20)
: ggml_metal_tuning::fa_vec_pick(
props_dev->device_id,
props_dev->gpu_family,
(int) op->src[1]->type,
(int) ne00, (int) ne20, // dk, dv (ne00 == dk for FA)
ggml/src/ggml-metal/ggml-metal-tuning.cpp
+1057 -3939
View File
File diff suppressed because it is too large Load Diff
ggml/src/ggml-metal/ggml-metal-tuning.h
+3 -5
View File
@@ -1,6 +1,5 @@
#pragma once
#include "ggml-metal-device.h" // enum ggml_metal_device_id
#include "ggml.h"
#include <cstdint>
@@ -32,7 +31,7 @@ constexpr int8_t FA_VEC_DOMAIN_DECODE = 0; // ne01 == 1
constexpr int8_t FA_VEC_DOMAIN_BATCH = 1; // ne01 >= 2
struct fa_vec_key_t {
int8_t device_id;
int8_t family;
int8_t dtype;
int16_t dk;
int16_t dv;
@@ -70,8 +69,7 @@ void fa_vec_set_override(fa_vec_cfg_t cfg);
void fa_vec_clear_override();
fa_vec_cfg_t fa_vec_baseline_cfg(int dk, int dv);
// device_id selects a per-SKU row; on a miss, gpu_family (0 if unknown) maps to a representative
// SKU and the table is retried. No match -> baseline.
fa_vec_cfg_t fa_vec_pick(enum ggml_metal_device_id device_id, int gpu_family, int dtype, int dk, int dv, int64_t ne11, int64_t ne01);
// Keyed by Apple GPU family; an untuned family matches no row and gets the baseline.
fa_vec_cfg_t fa_vec_pick(int gpu_family, int dtype, int dk, int dv, int64_t ne11, int64_t ne01);
} // namespace ggml_metal_tuning