From a9ef4afdf4a004559b6e8c2316b7b237113d9160 Mon Sep 17 00:00:00 2001 From: "Nat Kershaw (MSFT)" Date: Wed, 4 Dec 2024 16:38:27 -0800 Subject: [PATCH 1/2] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 11bda7e83..4ac897618 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ See documentation at https://onnxruntime.ai/docs/genai. |Platform| Linux
Windows
Mac ^
Android ^ ||iOS ||| |Architecture|x86
x64
Arm64 ~ |||| |Hardware Acceleration|CUDA
DirectML
|QNN
OpenVINO
ROCm || -|Features|| Interactive decoding
Customization (fine-tuning)| Speculative decoding | +|Features|MultiLoRA
Interactive decoding (session continuation)^ | Constrained decoding | Speculative decoding | \* The Llama model architecture supports similar model families such as CodeLlama, Vicuna, Yi, and more. From eb53587ed6e05b9cc6e34996ecb73d6de7367524 Mon Sep 17 00:00:00 2001 From: "Nat Kershaw (MSFT)" Date: Tue, 10 Dec 2024 17:07:07 -0800 Subject: [PATCH 2/2] Update README.md Co-authored-by: Baiju Meswani --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 4ac897618..6a8718ec7 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ See documentation at https://onnxruntime.ai/docs/genai. |Platform| Linux
Windows
Mac ^
Android ^ ||iOS ||| |Architecture|x86
x64
Arm64 ~ |||| |Hardware Acceleration|CUDA
DirectML
|QNN
OpenVINO
ROCm || -|Features|MultiLoRA
Interactive decoding (session continuation)^ | Constrained decoding | Speculative decoding | +|Features|MultiLoRA
Continuous decoding (session continuation)^ | Constrained decoding | Speculative decoding | \* The Llama model architecture supports similar model families such as CodeLlama, Vicuna, Yi, and more.