diff options
| author | Howard Su <howard0su@gmail.com> | 2023-07-13 21:58:25 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-07-13 21:58:25 +0800 |
| commit | 32c54116318929c90fd7ae814cf9b5232cd44c36 (patch) | |
| tree | 3b9126e3fb387ef1aa53d7461f9a41e1ce2965ed /examples/server | |
| parent | ff5d58faecf1f02b05bd015bdfc6a394cf2bc9ba (diff) | |
Revert "Support using mmap when applying LoRA (#2095)" (#2206)
Has perf regression when mlock is used.
This reverts commit 2347463201a9f4159ae95b737e1544dd300569c8.
Diffstat (limited to 'examples/server')
| -rw-r--r-- | examples/server/README.md | 2 | ||||
| -rw-r--r-- | examples/server/server.cpp | 3 |
2 files changed, 3 insertions, 2 deletions
diff --git a/examples/server/README.md b/examples/server/README.md index 3691abd..ad9b6bb 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -16,7 +16,7 @@ Command line options: - `--memory-f32`: Use 32-bit floats instead of 16-bit floats for memory key+value. Not recommended. - `--mlock`: Lock the model in memory, preventing it from being swapped out when memory-mapped. - `--no-mmap`: Do not memory-map the model. By default, models are mapped into memory, which allows the system to load only the necessary parts of the model as needed. -- `--lora FNAME`: Apply a LoRA (Low-Rank Adaptation) adapter to the model. This allows you to adapt the pretrained model to specific tasks or domains. +- `--lora FNAME`: Apply a LoRA (Low-Rank Adaptation) adapter to the model (implies --no-mmap). This allows you to adapt the pretrained model to specific tasks or domains. - `--lora-base FNAME`: Optional model to use as a base for the layers modified by the LoRA adapter. This flag is used in conjunction with the `--lora` flag, and specifies the base model for the adaptation. - `-to N`, `--timeout N`: Server read/write timeout in seconds. Default `600`. - `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`. diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 4114343..296c5d6 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -632,7 +632,7 @@ static void server_print_usage(const char *argv0, const gpt_params ¶ms, fprintf(stderr, " model path (default: %s)\n", params.model.c_str()); fprintf(stderr, " -a ALIAS, --alias ALIAS\n"); fprintf(stderr, " set an alias for the model, will be added as `model` field in completion response\n"); - fprintf(stderr, " --lora FNAME apply LoRA adapter\n"); + fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n"); fprintf(stderr, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n"); fprintf(stderr, " --host ip address to listen (default (default: %s)\n", sparams.hostname.c_str()); fprintf(stderr, " --port PORT port to listen (default (default: %d)\n", sparams.port); @@ -820,6 +820,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, break; } params.lora_adapter = argv[i]; + params.use_mmap = false; } else if (arg == "--lora-base") { |