vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
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;
}
if (slot.state != SLOT_STATE_GENERATING) {
continue;
}
llama_token id = slot.sampled;
struct common_speculative_params params_spec;