tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : add some missing env variables (#9116)

Browse Source 
* server : add some missing env variables

* add LLAMA_ARG_HOST to server dockerfile

* also add LLAMA_ARG_CONT_BATCHING
This commit is contained in:
Xuan Son Nguyen
2024-08-27 11:07:01 +02:00
committed by GitHub
parent 2e59d61c1b
commit a77feb5d71
7 changed files with 60 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
common/common.cpp
View File

@ -327,6 +327,10 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
void gpt_params_parse_from_env(gpt_params & params) {
// we only care about server-related params for now
get_env("LLAMA_ARG_MODEL", params.model);
get_env("LLAMA_ARG_MODEL_URL", params.model_url);
get_env("LLAMA_ARG_MODEL_ALIAS", params.model_alias);
get_env("LLAMA_ARG_HF_REPO", params.hf_repo);
get_env("LLAMA_ARG_HF_FILE", params.hf_file);
get_env("LLAMA_ARG_THREADS", params.n_threads);
get_env("LLAMA_ARG_CTX_SIZE", params.n_ctx);
get_env("LLAMA_ARG_N_PARALLEL", params.n_parallel);
@ -341,6 +345,9 @@ void gpt_params_parse_from_env(gpt_params & params) {
get_env("LLAMA_ARG_EMBEDDINGS", params.embedding);
get_env("LLAMA_ARG_FLASH_ATTN", params.flash_attn);
get_env("LLAMA_ARG_DEFRAG_THOLD", params.defrag_thold);
get_env("LLAMA_ARG_CONT_BATCHING", params.cont_batching);
get_env("LLAMA_ARG_HOST", params.hostname);
get_env("LLAMA_ARG_PORT", params.port);
}
bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {