diff --git a/docs/lora_optims.qmd b/docs/lora_optims.qmd index 3f8276bc5..eaeeed260 100644 --- a/docs/lora_optims.qmd +++ b/docs/lora_optims.qmd @@ -12,6 +12,7 @@ to leverage operator fusion and tensor re-use in order to improve speed and redu memory usage during the forward and backward passes of these calculations. We currently support several common model architectures, including (but not limited to): + - `llama` - `mistral` - `qwen2`