diff options
| author | Pierrick Hymbert <pierrick.hymbert@gmail.com> | 2024-03-01 12:39:06 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-03-01 13:39:06 +0200 |
| commit | 3ab8b3a92ede46df88bc5a2dfca3777de4a2b2b6 (patch) | |
| tree | b0232b770527ead35c5a59971a0802ded16e8c40 /scripts/compare-llama-bench.py | |
| parent | 9600d59e010c18f5872580a21734ea1bf1968d04 (diff) | |
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 <slarengh@gmail.com>
Diffstat (limited to 'scripts/compare-llama-bench.py')
| -rwxr-xr-x | scripts/compare-llama-bench.py | 2 |
1 files changed, 1 insertions, 1 deletions
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. |