From 4399f13fb9462cd06f3f154d0aee738425000fea Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Thu, 4 Apr 2024 09:34:58 +0300 Subject: [PATCH] server : remove obsolete --memory-f32 option --- examples/server/README.md | 1 - examples/server/server.cpp | 2 -- 2 files changed, 3 deletions(-) diff --git a/examples/server/README.md b/examples/server/README.md index 626d55d4b11db..0d8564a1f97a9 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -30,7 +30,6 @@ The project is under active development, and we are [looking for feedback and co - `-ts SPLIT, --tensor-split SPLIT`: When using multiple GPUs, this option controls how large tensors should be split across all GPUs. `SPLIT` is a comma-separated list of non-negative values that assigns the proportion of data that each GPU should get in order. For example, "3,2" will assign 60% of the data to GPU 0 and 40% to GPU 1. By default, the data is split in proportion to VRAM, but this may not be optimal for performance. - `-b N`, `--batch-size N`: Set the batch size for prompt processing. Default: `2048` - `-ub N`, `--ubatch-size N`: Physical maximum batch size. Default: `512` -- `--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. - `--numa STRATEGY`: Attempt one of the below optimization strategies that may help on some NUMA systems diff --git a/examples/server/server.cpp b/examples/server/server.cpp index c60be2613073f..183f0d3c87af5 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -2189,8 +2189,6 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co printf(" KV cache defragmentation threshold (default: %.1f, < 0 - disabled)\n", params.defrag_thold); printf(" -b N, --batch-size N logical maximum batch size (default: %d)\n", params.n_batch); printf(" -ub N, --ubatch-size N physical maximum batch size (default: %d)\n", params.n_ubatch); - printf(" --memory-f32 use f32 instead of f16 for memory key+value (default: disabled)\n"); - printf(" not recommended: doubles context memory required and no measurable increase in quality\n"); if (llama_supports_mlock()) { printf(" --mlock force system to keep model in RAM rather than swapping or compressing\n"); }