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

fix ci errors

Browse source
This commit is contained in:
FSSRepo 2023-10-03 17:43:32 -04:00
parent 6da48f7485
commit 13916dcf6c
3 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server-parallel/README.md
View file

@ -20,4 +20,4 @@ server-parallel.exe -m models\7B\ggml-model.gguf --ctx_size 2048 -t 4 -ngl 33 --
The above command will start a server that by default listens on `127.0.0.1:8080`. The above command will start a server that by default listens on `127.0.0.1:8080`.
You can consume the endpoints with Postman or NodeJS with axios library. You can visit the web front end at the same url. You can consume the endpoints with Postman or NodeJS with axios library. You can visit the web front end at the same url.
# This example is a Proof of Concept, have bugs and unexpected behaivors # This example is a Proof of Concept, have bugs and unexpected behaivors

2
examples/server-parallel/index.h
View file

@ -152,4 +152,4 @@ const auto index_html = R"(
</script> </script>
</body> </body>
</html> </html>
)"; )";

6
examples/server-parallel/server.cpp
View file

@ -249,7 +249,7 @@ struct server_parallel_context {
request_clean_kv = false; request_clean_kv = false;
LOG_TEE("%s: clearing the KV cache\n", __func__); LOG_TEE("%s: clearing the KV cache\n", __func__);
} }
// assign workload to the slots // assign workload to the slots
if (params.cont_batching || batch.n_tokens == 0) { if (params.cont_batching || batch.n_tokens == 0) {
for (llama_client_slot & slot : slots) { for (llama_client_slot & slot : slots) {
@ -287,7 +287,7 @@ struct server_parallel_context {
} }
} }
} }
if (batch.n_tokens == 0) { if (batch.n_tokens == 0) {
return true; return true;
} }
@ -806,4 +806,4 @@ int main(int argc, char **argv)
{ {
return 1; return 1;
} }
} }