root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-05 16:24:34 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

server : update prompt on slot restore (#9800)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-10-11 09:16:00 +03:00
parent 0fb9c91f14
commit 3ae86704e6
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
examples/server/server.cpp
View File

@ -1778,6 +1778,9 @@ struct server_context {
}
slot->cache_tokens.resize(token_count);
// TODO: maybe detokenize the slot->cache_tokens instead?
slot->prompt = string_format("[restored %d tokens from file]", (int) token_count);
const int64_t t_end = ggml_time_us();
const double t_restore_ms = (t_end - t_start) / 1000.0;