mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-27 15:41:19 +02:00
YiChen Lv
f280b26983
* metal : per-device tuned (Q, NE) for flash-attn vec (#25750)
* rebase Q-generic FA vec body from 01dc93607 (#23114)
* add 53 f16 (Q,NE) flash-attn vec instantiations (vec 80 -> 133)
* add FA vec (Q,NE) tuning table + dispatch wiring + SMEM cap fallback
* add FA vec (Q,NE) perf sweep
* fill tuning result
* fold family table into a per-family representative SKU
* refactor tuning result format
* extend FA vec tuning to quantized KV caches
* sync fa vec tuner bucketing with runtime, use pointwise tuning regret
* update tuned table
* format and cleanup
* prefix fa_vec tuning procs with ggml_backend_metal_tuning_, drop unused fa_vec_override_active
* add device id -> token lookup for the offline tuning tool
* add ggml-metal-tuning skeleton
* add op-agnostic perf cell + median timing for the tuner
* add FA-vec graph build + tensor init to the tuner
* tools : add FA-vec (Q,NE) sweep, compression and table emit
* cool down and re-measure the dirty window on thermal drift
* test-backend-ops : replace the FA vec tune mode with a bounded (Q,NE) slice
* tools : document the Metal tuner, point the table comment at it
* abort on unknown KV type, single-source fa_vec_legal_ne
* cleanup
* honor -o in the FA vec (Q,NE) slice
* retune FA-vec (Q, NE) under a pointwise no-harm gate
* cont : add fa-vec tunings for M1 Pro, M2 Ultra, M5 Max
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
19 lines
703 B
C
19 lines
703 B
C
#pragma once
|
|
|
|
#include "ggml-backend.h"
|
|
|
|
struct tuner_opts {
|
|
const char * dtype_filter = nullptr; // comma-separated, e.g. "f16,q4_0"; null = all
|
|
const char * dk_filter = nullptr; // comma-separated dk values, e.g. "128,192"; null = all
|
|
int reps = 7;
|
|
unsigned seed = 1234;
|
|
bool cooldown = true;
|
|
double cool_drift = 0.10;
|
|
double cool_eps = 0.03;
|
|
int cool_max_wait = 120;
|
|
int cool_max_retry = 2;
|
|
};
|
|
|
|
// Returns false only when the required Metal proc bridges are unavailable.
|
|
bool tuner_fa_vec_run(ggml_backend_t backend, ggml_backend_dev_t dev, const tuner_opts & opts);
|