From 3ab8b3a92ede46df88bc5a2dfca3777de4a2b2b6 Mon Sep 17 00:00:00 2001 From: Pierrick Hymbert Date: Fri, 1 Mar 2024 12:39:06 +0100 Subject: llama : cleanup unused mmq flags (#5772) * cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q * remove: mul_mat_q in compare llama bench and usage * update llama-bench --------- Co-authored-by: slaren --- scripts/compare-llama-bench.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts/compare-llama-bench.py') diff --git a/scripts/compare-llama-bench.py b/scripts/compare-llama-bench.py index 70737f97..39c3e52e 100755 --- a/scripts/compare-llama-bench.py +++ b/scripts/compare-llama-bench.py @@ -31,7 +31,7 @@ PRETTY_NAMES = { "model_size": "Model Size [GiB]", "model_n_params": "Num. of Parameters", "n_batch": "Batch size", "n_threads": "Threads", "type_k": "K type", "type_v": "V type", "n_gpu_layers": "GPU layers", "main_gpu": "Main GPU", "no_kv_offload": "NKVO", - "mul_mat_q": "MMQ", "tensor_split": "Tensor split" + "tensor_split": "Tensor split" } DEFAULT_SHOW = ["model_type"] # Always show these properties by default. -- cgit v1.2.3