upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-03 08:30:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

fit : wrap llama_device_memory_data

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-12 18:12:24 +03:00
parent 02182fc5b9
commit 3518061868
3 changed files with 40 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tools/server/server-context.cpp
View File

@@ -866,10 +866,7 @@ private:
}
for (size_t j = 0; j < devs.size(); ++j) {
const size_t bytes =
(measure_model_bytes ? dmd[j].mb.model : 0) +
dmd[j].mb.context +
dmd[j].mb.compute;
const size_t bytes = (measure_model_bytes ? dmd[j].model : 0) + dmd[j].context + dmd[j].compute;
total += bytes;
for (size_t i = 0; i < tgt_devices.size(); i++) {
if (tgt_devices[i] == devs[j]) {