From 1c641e6aac5c18b964e7b32d9dbbb4bf5301d0d7 Mon Sep 17 00:00:00 2001 From: Olivier Chafik Date: Thu, 13 Jun 2024 00:41:52 +0100 Subject: =?UTF-8?q?`build`:=20rename=20main=20=E2=86=92=20llama-cli,=20ser?= =?UTF-8?q?ver=20=E2=86=92=20llama-server,=20llava-cli=20=E2=86=92=20llama?= =?UTF-8?q?-llava-cli,=20etc...=20(#7809)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * `main`/`server`: rename to `llama` / `llama-server` for consistency w/ homebrew * server: update refs -> llama-server gitignore llama-server * server: simplify nix package * main: update refs -> llama fix examples/main ref * main/server: fix targets * update more names * Update build.yml * rm accidentally checked in bins * update straggling refs * Update .gitignore * Update server-llm.sh * main: target name -> llama-cli * Prefix all example bins w/ llama- * fix main refs * rename {main->llama}-cmake-pkg binary * prefix more cmake targets w/ llama- * add/fix gbnf-validator subfolder to cmake * sort cmake example subdirs * rm bin files * fix llama-lookup-* Makefile rules * gitignore /llama-* * rename Dockerfiles * rename llama|main -> llama-cli; consistent RPM bin prefixes * fix some missing -cli suffixes * rename dockerfile w/ llama-cli * rename(make): llama-baby-llama * update dockerfile refs * more llama-cli(.exe) * fix test-eval-callback * rename: llama-cli-cmake-pkg(.exe) * address gbnf-validator unused fread warning (switched to C++ / ifstream) * add two missing llama- prefixes * Updating docs for eval-callback binary to use new `llama-` prefix. * Updating a few lingering doc references for rename of main to llama-cli * Updating `run-with-preset.py` to use new binary names. Updating docs around `perplexity` binary rename. * Updating documentation references for lookup-merge and export-lora * Updating two small `main` references missed earlier in the finetune docs. * Update apps.nix * update grammar/README.md w/ new llama-* names * update llama-rpc-server bin name + doc * Revert "update llama-rpc-server bin name + doc" This reverts commit e474ef1df481fd8936cd7d098e3065d7de378930. * add hot topic notice to README.md * Update README.md * Update README.md * rename gguf-split & quantize bins refs in **/tests.sh --------- Co-authored-by: HanClinto --- scripts/run-with-preset.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'scripts/run-with-preset.py') diff --git a/scripts/run-with-preset.py b/scripts/run-with-preset.py index 0d721911..ee21eab3 100755 --- a/scripts/run-with-preset.py +++ b/scripts/run-with-preset.py @@ -10,7 +10,7 @@ import yaml logger = logging.getLogger("run-with-preset") -CLI_ARGS_MAIN_PERPLEXITY = [ +CLI_ARGS_LLAMA_CLI_PERPLEXITY = [ "batch-size", "cfg-negative-prompt", "cfg-scale", "chunks", "color", "ctx-size", "escape", "export", "file", "frequency-penalty", "grammar", "grammar-file", "hellaswag", "hellaswag-tasks", "ignore-eos", "in-prefix", "in-prefix-bos", "in-suffix", @@ -29,7 +29,7 @@ CLI_ARGS_LLAMA_BENCH = [ "n-prompt", "output", "repetitions", "tensor-split", "threads", "verbose" ] -CLI_ARGS_SERVER = [ +CLI_ARGS_LLAMA_SERVER = [ "alias", "batch-size", "ctx-size", "embedding", "host", "memory-f32", "lora", "lora-base", "low-vram", "main-gpu", "mlock", "model", "n-gpu-layers", "n-probs", "no-mmap", "no-mul-mat-q", "numa", "path", "port", "rope-freq-base", "timeout", "rope-freq-scale", "tensor-split", @@ -37,7 +37,7 @@ CLI_ARGS_SERVER = [ ] description = """Run llama.cpp binaries with presets from YAML file(s). -To specify which binary should be run, specify the "binary" property (main, perplexity, llama-bench, and server are supported). +To specify which binary should be run, specify the "binary" property (llama-cli, llama-perplexity, llama-bench, and llama-server are supported). To get a preset file template, run a llama.cpp binary with the "--logdir" CLI argument. Formatting considerations: @@ -77,19 +77,19 @@ for yaml_file in known_args.yaml_files: props = {prop.replace("_", "-"): val for prop, val in props.items()} -binary = props.pop("binary", "main") +binary = props.pop("binary", "llama-cli") if known_args.binary: binary = known_args.binary if os.path.exists(f"./{binary}"): binary = f"./{binary}" -if binary.lower().endswith("main") or binary.lower().endswith("perplexity"): - cli_args = CLI_ARGS_MAIN_PERPLEXITY +if binary.lower().endswith("llama-cli") or binary.lower().endswith("llama-perplexity"): + cli_args = CLI_ARGS_LLAMA_CLI_PERPLEXITY elif binary.lower().endswith("llama-bench"): cli_args = CLI_ARGS_LLAMA_BENCH -elif binary.lower().endswith("server"): - cli_args = CLI_ARGS_SERVER +elif binary.lower().endswith("llama-server"): + cli_args = CLI_ARGS_LLAMA_SERVER else: logger.error(f"Unknown binary: {binary}") sys.exit(1) -- cgit v1.2.3