happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

arg: add -mm and -mmu as short form of --mmproj and --mmproj-url (#17958) 

* arg: add -mm and -mmu as short form of --mmproj and --mmproj-url

* correct order

* update docs
This commit is contained in:
Xuan-Son Nguyen 2025-12-12 14:06:06 +01:00 committed by GitHub
parent dada4c846d
commit 54a0fee4b7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
common/arg.cpp
View File

@ -1856,7 +1856,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
} }
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING")); ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING"));
add_opt(common_arg( add_opt(common_arg(
{"--mmproj"}, "FILE", {"-mm", "--mmproj"}, "FILE",
"path to a multimodal projector file. see tools/mtmd/README.md\n" "path to a multimodal projector file. see tools/mtmd/README.md\n"
"note: if -hf is used, this argument can be omitted", "note: if -hf is used, this argument can be omitted",
[](common_params & params, const std::string & value) { [](common_params & params, const std::string & value) {
@ -1864,7 +1864,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
} }
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ")); ).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ"));
add_opt(common_arg( add_opt(common_arg(
{"--mmproj-url"}, "URL", {"-mmu", "--mmproj-url"}, "URL",
"URL to a multimodal projector file. see tools/mtmd/README.md", "URL to a multimodal projector file. see tools/mtmd/README.md",
[](common_params & params, const std::string & value) { [](common_params & params, const std::string & value) {
params.mmproj.url = value; params.mmproj.url = value;

4
tools/server/README.md
View File

@ -166,8 +166,8 @@ For the ful list of features, please refer to [server's changelog](https://githu
| `--pooling {none,mean,cls,last,rank}` | pooling type for embeddings, use model default if unspecified<br/>(env: LLAMA_ARG_POOLING) | | `--pooling {none,mean,cls,last,rank}` | pooling type for embeddings, use model default if unspecified<br/>(env: LLAMA_ARG_POOLING) |
| `-cb, --cont-batching` | enable continuous batching (a.k.a dynamic batching) (default: enabled)<br/>(env: LLAMA_ARG_CONT_BATCHING) | | `-cb, --cont-batching` | enable continuous batching (a.k.a dynamic batching) (default: enabled)<br/>(env: LLAMA_ARG_CONT_BATCHING) |
| `-nocb, --no-cont-batching` | disable continuous batching<br/>(env: LLAMA_ARG_NO_CONT_BATCHING) | | `-nocb, --no-cont-batching` | disable continuous batching<br/>(env: LLAMA_ARG_NO_CONT_BATCHING) |
| `--mmproj FILE` | path to a multimodal projector file. see tools/mtmd/README.md<br/>note: if -hf is used, this argument can be omitted<br/>(env: LLAMA_ARG_MMPROJ) | | `-mm, --mmproj FILE` | path to a multimodal projector file. see tools/mtmd/README.md<br/>note: if -hf is used, this argument can be omitted<br/>(env: LLAMA_ARG_MMPROJ) |
| `--mmproj-url URL` | URL to a multimodal projector file. see tools/mtmd/README.md<br/>(env: LLAMA_ARG_MMPROJ_URL) | | `-mmu, --mmproj-url URL` | URL to a multimodal projector file. see tools/mtmd/README.md<br/>(env: LLAMA_ARG_MMPROJ_URL) |
| `--no-mmproj` | explicitly disable multimodal projector, useful when using -hf<br/>(env: LLAMA_ARG_NO_MMPROJ) | | `--no-mmproj` | explicitly disable multimodal projector, useful when using -hf<br/>(env: LLAMA_ARG_NO_MMPROJ) |
| `--no-mmproj-offload` | do not offload multimodal projector to GPU<br/>(env: LLAMA_ARG_NO_MMPROJ_OFFLOAD) | | `--no-mmproj-offload` | do not offload multimodal projector to GPU<br/>(env: LLAMA_ARG_NO_MMPROJ_OFFLOAD) |
| `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MIN_TOKENS) | | `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MIN_TOKENS) |