ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

[NPU] Small update about zip doc (#12951)

Browse source
This commit is contained in:
binbin Deng 2025-03-07 15:22:14 +08:00 committed by GitHub
parent 015a4c8c43
commit 5ee09b4b28
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 8 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/mddocs/Quickstart/llama_cpp_npu_portable_zip_quickstart.md
View file

@ -65,6 +65,10 @@ You could then use cli tool to run GGUF models on Intel NPU through running `lla
llama-cli-npu.exe -m DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf -n 32 --prompt "What is AI?" llama-cli-npu.exe -m DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf -n 32 --prompt "What is AI?"
``` ```
> [!Note]
>
> - The supported maximum number of input tokens is 960, and maximum sequence length for both input and output tokens is 1024 currently.
## Troubleshooting ## Troubleshooting
### `L0 pfnCreate2 result: ZE_RESULT_ERROR_INVALID_ARGUMENT, code 0x78000004` error ### `L0 pfnCreate2 result: ZE_RESULT_ERROR_INVALID_ARGUMENT, code 0x78000004` error

4
docs/mddocs/Quickstart/llama_cpp_npu_portable_zip_quickstart.zh-CN.md
View file

@ -65,6 +65,10 @@ IPEX-LLM 提供了 llama.cpp 的相关支持以在 Intel NPU 上运行 GGUF 模
llama-cli-npu.exe -m DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf -n 32 --prompt "What is AI?" llama-cli-npu.exe -m DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf -n 32 --prompt "What is AI?"
``` ```
> [!Note]
>
> - 目前支持的输入token数上限是960，输入和输出总token数上限是1024。
## 故障排除 ## 故障排除
### `L0 pfnCreate2 result: ZE_RESULT_ERROR_INVALID_ARGUMENT, code 0x78000004` 报错 ### `L0 pfnCreate2 result: ZE_RESULT_ERROR_INVALID_ARGUMENT, code 0x78000004` 报错