tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : do not speculate during prompt processing

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-12-03 10:58:43 +02:00
parent 642330ac7c
commit 33d7b70c88
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

@ -2322,6 +2322,10 @@ struct server_context {
continue; continue;
} }
if (slot.state != SLOT_STATE_GENERATING) {
continue;
}
llama_token id = slot.sampled; llama_token id = slot.sampled;
struct common_speculative_params params_spec; struct common_speculative_params params_spec;