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

Opt class for positional argument handling (#10508)

Browse source 
Added support for positional arguments `model` and `prompt`. Added
functionality to download via strings like:

  llama-run llama3
  llama-run ollama://granite-code
  llama-run ollama://granite-code:8b
  llama-run hf://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf
  llama-run huggingface://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf
  llama-run https://example.com/some-file1.gguf
  llama-run some-file2.gguf
  llama-run file://some-file3.gguf

Signed-off-by: Eric Curtin <ecurtin@redhat.com>
This commit is contained in:
Eric Curtin 2024-12-13 18:34:25 +00:00 • committed by GitHub
parent 11e07fd63b
commit c27ac678dd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 542 additions and 163 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/CMakeLists.txt
View file

@ -81,7 +81,7 @@ set(LLAMA_COMMON_EXTRA_LIBS build_info)
# Use curl to download model url
if (LLAMA_CURL)
find_package(CURL REQUIRED)
add_definitions(-DLLAMA_USE_CURL)
target_compile_definitions(${TARGET} PUBLIC LLAMA_USE_CURL)
include_directories(${CURL_INCLUDE_DIRS})
find_library(CURL_LIBRARY curl REQUIRED)
set(LLAMA_COMMON_EXTRA_LIBS ${LLAMA_COMMON_EXTRA_LIBS} ${CURL_LIBRARY})

6
common/common.cpp
View file

@ -1076,12 +1076,6 @@ struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const cpu_p
#define CURL_MAX_RETRY 3
#define CURL_RETRY_DELAY_SECONDS 2
static bool starts_with(const std::string & str, const std::string & prefix) {
// While we wait for C++20's std::string::starts_with...
return str.rfind(prefix, 0) == 0;
}
static bool curl_perform_with_retry(const std::string& url, CURL* curl, int max_attempts, int retry_delay_seconds) {
int remaining_attempts = max_attempts;

11
common/common.h
View file

@ -37,9 +37,9 @@ using llama_tokens = std::vector<llama_token>;
// build info
extern int LLAMA_BUILD_NUMBER;
extern char const * LLAMA_COMMIT;
extern char const * LLAMA_COMPILER;
extern char const * LLAMA_BUILD_TARGET;
extern const char * LLAMA_COMMIT;
extern const char * LLAMA_COMPILER;
extern const char * LLAMA_BUILD_TARGET;
struct common_control_vector_load_info;
@ -437,6 +437,11 @@ std::vector<std::string> string_split<std::string>(const std::string & input, ch
return parts;
}
static bool string_starts_with(const std::string & str,
const std::string & prefix) { // While we wait for C++20's std::string::starts_with...
return str.rfind(prefix, 0) == 0;
}
bool string_parse_kv_override(const char * data, std::vector<llama_model_kv_override> & overrides);
void string_process_escapes(std::string & input);