WasmEdge / WasmEdge

WasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It powers serverless apps, embedded functions, microservices, smart contracts, and IoT devices.

Home Page:https://WasmEdge.org

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

bug: LlamaEdge 0.4.0 installation on Mac Intel model, missing file ' WasmEdge-plugin-wasmedge_rustls-0.13.5-darwin_x86_64.tar.gz'

hintcnuie opened this issue · comments

Summary

Env:
MacOS 14.2.1, CPU: Intel Core i9

Issue Description:

when doing excise following guild LlamaEdge v0.4.0 新版发布,添加 RAG 和 Llava 支持, input the command:

bash <(curl -sSfL 'https://raw.githubusercontent.com/LlamaEdge/LlamaEdge/main/run-llm.sh') --model llama-2-7b-chat

Command output:

[+] Downloading the selected model from https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/resolve/main/Llama-2-7b-chat-hf-Q5_K_M.gguf
################################################################################################################### 100.0%################################################################################################################### 100.0%
[+] Extracting prompt type: llama-2-chat
[+] No reverse prompt required
[+] Install WasmEdge with wasi-nn_ggml plugin ...

Using Python: /usr/local/bin/python3
INFO - CUDA is only supported on Linux
INFO - CUDA is only supported on Linux
WARNING - Experimental Option Selected: plugins
WARNING - plugins option may change later
INFO - Compatible with current configuration
INFO - Running Uninstaller
WARNING - SHELL variable not found. Using zsh as SHELL
INFO - shell configuration updated
INFO - Downloading WasmEdge
|============================================================|100.00 %INFO - Downloaded
INFO - Installing WasmEdge
INFO - WasmEdge Successfully installed
INFO - Downloading Plugin: wasi_nn-ggml
|============================================================|100.00 %INFO - Downloaded
INFO - Downloading Plugin: wasmedge_rustls
ERROR - Download error from urllib: HTTP Error 404: Not Found
ERROR - URL: https://github.com/WasmEdge/WasmEdge/releases/download/0.13.5/WasmEdge-plugin-wasmedge_rustls-0.13.5-darwin_x86_64.tar.gz
Failed to install WasmEdge

See the screenshot:
Screenshot 2024-03-04 at 22 01 44

Issue:

There is no installation file for Mac Intel x86_64 model, but Mac Arm64 model.

Current file: WasmEdge-plugin-wasmedge_rustls-0.13.5-darwin_arm64.tar.gz
Missing:
https://github.com/WasmEdge/WasmEdge/releases/download/0.13.5/WasmEdge-plugin-wasmedge_rustls-0.13.5-darwin_x86_64.tar.gz

Current State

Installation LlamaEdge failed:

  1. Download GGUF model successfully
    2.Install WasmEdge rustls 1.3.5 failed on Mac Intel model.

Expected State

Installation LlamaEdge successfully and start the Bot:

  1. Download GGUF model successfully
    2.Install WasmEdge rustls 1.3.5 successfully .

Reproduction steps

Execute the command on Mac Intel model.

bash <(curl -sSfL 'https://raw.githubusercontent.com/LlamaEdge/LlamaEdge/main/run-llm.sh') --model llama-2-7b-chat

Screenshots

Screenshot 2024-03-04 at 22 01 44

Any logs you want to share for showing the specific issue

[+] Downloading the selected model from https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/resolve/main/Llama-2-7b-chat-hf-Q5_K_M.gguf
################################################################################################################### 100.0%################################################################################################################### 100.0%
[+] Extracting prompt type: llama-2-chat
[+] No reverse prompt required
[+] Install WasmEdge with wasi-nn_ggml plugin ...

Using Python: /usr/local/bin/python3
INFO - CUDA is only supported on Linux
INFO - CUDA is only supported on Linux
WARNING - Experimental Option Selected: plugins
WARNING - plugins option may change later
INFO - Compatible with current configuration
INFO - Running Uninstaller
WARNING - SHELL variable not found. Using zsh as SHELL
INFO - shell configuration updated
INFO - Downloading WasmEdge
|============================================================|100.00 %INFO - Downloaded
INFO - Installing WasmEdge
INFO - WasmEdge Successfully installed
INFO - Downloading Plugin: wasi_nn-ggml
|============================================================|100.00 %INFO - Downloaded
INFO - Downloading Plugin: wasmedge_rustls
ERROR - Download error from urllib: HTTP Error 404: Not Found
ERROR - URL: https://github.com/WasmEdge/WasmEdge/releases/download/0.13.5/WasmEdge-plugin-wasmedge_rustls-0.13.5-darwin_x86_64.tar.gz
Failed to install WasmEdge

Components

CLI

WasmEdge Version or Commit you used

0.13.5

Operating system information

MacOS 14.2.1, Intel CPU

Hardware Architecture

X86_64

Compiler flags and options

No response

@hintcnuie
Just updated the release assets, please try again.

yes, the new version of WasmEdge and new plugin rustls is installed, confirmed from log:
bash <(curl -sSfL 'https://raw.githubusercontent.com/LlamaEdge/LlamaEdge/main/run-llm.sh')

[+] Installing WasmEdge with wasi-nn_ggml plugin ...

Using Python: /usr/local/bin/python3
INFO - CUDA is only supported on Linux
INFO - CUDA is only supported on Linux
WARNING - Experimental Option Selected: plugins
WARNING - plugins option may change later
INFO - Compatible with current configuration
INFO - Running Uninstaller
ls: /Users/Think/.wasmedge: No such file or directory
WARNING - SHELL variable not found. Using zsh as SHELL
INFO - shell configuration updated
INFO - Downloading WasmEdge
|============================================================|100.00 %INFO - Downloaded
INFO - Installing WasmEdge
INFO - WasmEdge Successfully installed
INFO - Downloading Plugin: wasi_nn-ggml
|============================================================|100.00 %INFO - Downloaded
INFO - Downloading Plugin: wasmedge_rustls
|============================================================|100.00 %INFO - Downloaded
INFO - Run:
source /Users/Think/.zshenv

The WasmEdge Runtime is installed in /Users/Think/.wasmedge/bin/wasmedge.

nice work! quick response! @hydai