nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 20 Packages Projects Releases Wiki Activity

metal : reduce rset heartbeat from 500ms -> 5ms (#24074)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-04 08:05:32 +03:00
committed by GitHub
parent e8c54893f2
commit 3d1998634e
1 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-device.m
+8 -4
View File
@@ -547,6 +547,8 @@ struct ggml_metal_rsets {
// number of seconds since the last graph computation // number of seconds since the last graph computation
// keep the residency sets wired for that amount of time to avoid being collected by the OS // keep the residency sets wired for that amount of time to avoid being collected by the OS
int keep_alive_s; int keep_alive_s;
int loops_per_s;
int time_per_loop_ms;
// background heartbeat thread to keep the residency sets alive // background heartbeat thread to keep the residency sets alive
atomic_bool d_stop; atomic_bool d_stop;
@@ -573,10 +575,13 @@ ggml_metal_rsets_t ggml_metal_rsets_init(void) {
res->keep_alive_s = 3*60; res->keep_alive_s = 3*60;
} }
res->time_per_loop_ms = 5;
res->loops_per_s = 1000/res->time_per_loop_ms;
GGML_LOG_INFO("%s: creating a residency set collection (keep_alive = %d s)\n", __func__, res->keep_alive_s); GGML_LOG_INFO("%s: creating a residency set collection (keep_alive = %d s)\n", __func__, res->keep_alive_s);
atomic_store_explicit(&res->d_stop, false, memory_order_relaxed); atomic_store_explicit(&res->d_stop, false, memory_order_relaxed);
atomic_store_explicit(&res->d_loop, 2*res->keep_alive_s, memory_order_relaxed); atomic_store_explicit(&res->d_loop, res->loops_per_s*res->keep_alive_s, memory_order_relaxed);
res->d_group = dispatch_group_create(); res->d_group = dispatch_group_create();
@@ -599,8 +604,7 @@ ggml_metal_rsets_t ggml_metal_rsets_init(void) {
[res->lock unlock]; [res->lock unlock];
} }
// half a second usleep(res->time_per_loop_ms * 1000);
usleep(500 * 1000);
} }
} }
#endif #endif
@@ -979,7 +983,7 @@ void ggml_metal_device_rsets_keep_alive(ggml_metal_device_t dev) {
return; return;
} }
atomic_store_explicit(&dev->rsets->d_loop, 2*dev->rsets->keep_alive_s, memory_order_relaxed); atomic_store_explicit(&dev->rsets->d_loop, dev->rsets->loops_per_s*dev->rsets->keep_alive_s, memory_order_relaxed);
} }
struct ggml_metal_event { struct ggml_metal_event {