taeyeonlee

[BUG] The generated text is strange from 8 QNN Context Bins which are generated in AI Hub.

2

Dear Qualcomm, According to the Sample App ((QNN API C++ : https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html), I made an Android app using Android NDK C++ and pytorch to run the 8 QNN Context Bins...

QCT Genie SDK (genie-t2t-run) : Llama v2 7B performance

6

Llama v2 7B quantized model bin file (llama_qct_genie.bin) can run on Galaxy S23 Ultra using QCT Genie SDK (genie-t2t-run), but the performance of the Llama v2 7B quantized is so...

QCT Genie SDK (genie-t2t-run) fails to run on QNN HTP backend

3

**Describe the bug** QCT Genie SDK (genie-t2t-run) fails to run Llama2 7b model on QNN HTP backend, in my Android Mobile S24 Ultra. What does it mean ? The error...

[BUG] fails to create context from binary for the 4 QNN Context Bin files (llama_v2_7b_chat_quantized_TokenGenerator_x_Quantized.bin)

2

Hi, It fails to create context from binary for the 4 QNN Context Bin files (llama_v2_7b_chat_quantized_TokenGenerator_1_Quantized.bin, llama_v2_7b_chat_quantized_TokenGenerator_2_Quantized.bin, llama_v2_7b_chat_quantized_TokenGenerator_3_Quantized.bin, llama_v2_7b_chat_quantized_TokenGenerator_4_Quantized.bin), in the Android mobile S24 Ultra. even though it succeed to...

Android App to run Llama-v2-7B-Chat Quantized INT4 on my Android Device

8

Hi, Could you share the sample Android App to run Llama-v2-7B-Chat Quantized INT4 on my Android Device ? your sample "python -m qai_hub_models.models.llama_v2_7b_chat_quantized.export" generated the files below. Llama2_PromptProcessor_1_Quantized.onnx Llama2_PromptProcessor_1_Quantized.data Llama2_PromptProcessor_1_Quantized.encodings...

[BUG] genie-t2t-run Fails to run llama v2 7B quantized on Galaxy S23 Ultra

1

When running llama v2 7B quantized on QNN HTP backend of Snapdragon-Gen2, the error is following. What does it mean ? "Could not create context from binary for context index...

Hi, Android NDK Application (using GENIE C API) fails to run llama v2 7B quantized on Galaxy S24 Ultra. It succeeds to create the dialog config. (GenieDialogConfig_createFromJson). But, it fails...

### Description of the bug: Dear Google, What is the Max length for the prompt for the Gemini 1.5 Flash Android model ? When using the case 1 prompt, the...