Merge pull request #15 from kerthcet/feat/support-hf

remove ollama support

Author: InftyAI-Agent

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,12 +1,3 @@
-<!--  Thanks for sending a pull request!  Here are some tips for you:
-1. If this is your first time, please read our contributor guidelines: https://git.k8s.io/community/contributors/guide/first-contribution.md#your-first-contribution and developer guide https://git.k8s.io/community/contributors/devel/development.md#development-guide
-2. Please label this pull request according to what type of issue you are addressing, especially if this is a release targeted pull request. For reference on required PR/issue labels, read here:
-https://git.k8s.io/community/contributors/devel/sig-release/release.md#issuepr-kind-label
-3. Ensure you have added or ran the appropriate tests for your PR: https://git.k8s.io/community/contributors/devel/sig-testing/testing.md
-4. If you want *faster* PR reviews, read how: https://git.k8s.io/community/contributors/guide/pull-requests.md#best-practices-for-faster-reviews
-5. If the PR is unfinished, see how to mark it: https://git.k8s.io/community/contributors/guide/pull-requests.md#marking-unfinished-pull-requests
--->
-
 #### What this PR does / why we need it
 
 #### Which issue(s) this PR fixes

.github/workflows/kube-workflow-init.yaml

@@ -5,6 +5,6 @@ on:
 
 jobs:
   init:
-    uses: kerthcet/github-workflow-as-kube/.github/workflows/workflow-as-kubernetes-init.yaml@v0.1.3
+    uses: kerthcet/github-workflow-as-kube/.github/workflows/workflow-as-kubernetes-init.yaml@main
     secrets:
       AGENT_TOKEN: ${{ secrets.AGENT_TOKEN }}

.github/workflows/kube-workflow.yaml

@@ -16,6 +16,6 @@ on:
 
 jobs:
   event-handler:
-    uses: kerthcet/github-workflow-as-kube/.github/workflows/workflow-as-kubernetes.yaml@v0.1.3
+    uses: kerthcet/github-workflow-as-kube/.github/workflows/workflow-as-kubernetes.yaml@main
     secrets:
       AGENT_TOKEN: ${{ secrets.AGENT_TOKEN }}

Cargo.toml

@@ -2,7 +2,7 @@
 name = "puma"
 version = "0.0.1"
 edition = "2021"
-description = "A lightweight, high-performance inference engine for heterogeneous devices."
+description = "A lightweight, high-performance inference engine for local AI."
 license = "Apache-2.0"
 
 [dependencies]

README.md

@@ -1,6 +1,6 @@
 # PUMA
 
-Puma aims to be a lightweight, high-performance inference engine for heterogeneous devices. *Currently under active development.*
+**PUMA** aims to be a lightweight, high-performance inference engine for local AI. Play for fun.
 
 ## How to Run
 

src/cli/cmds.rs src/cli/commands.rssrc/cli/cmds.rs renamed to src/cli/commands.rs

@@ -1,9 +1,6 @@
 use clap::{Parser, Subcommand};
 use prettytable::{format, row, Table};
 
-use crate::downloader::ollama::OllamaDownloader;
-use crate::util::file;
-
 #[derive(Parser)]
 #[command(name = "PUMA")]
 #[command(about = "PUMA CLI")]
@@ -14,24 +11,22 @@ pub struct Cli {
 
 #[derive(Subcommand)]
 enum Commands {
-    /// List running inference services
+    /// List running models
     PS,
     /// List local models
     LS,
     /// Download a model from a model provider
     PULL(PullArgs),
-    /// Create and run a new inference service from a model
+    /// Create and run a new model
     RUN,
-    /// Stop one running inference service
+    /// Stop one running model
     STOP,
     /// Remove one model
     RM,
     /// Display system-wide information
     INFO,
-    /// Return detailed information about inference service
+    /// Return detailed information about a model
     INSPECT,
-    /// Return detailed information about model
-    SHOW,
     /// Returns the version of PUMA.
     VERSION,
 }
@@ -47,7 +42,6 @@ struct PullArgs {
 #[derive(Debug, Clone, clap::ValueEnum)]
 pub enum Provider {
     Huggingface,
-    Ollama,
     Modelscope,
 }
 
@@ -71,56 +65,39 @@ pub async fn run(cli: Cli) {
                 "Running",
                 "8m",
             ]);
-            table.add_row(row!["llama3-8b", "ollama", "llama3.1:8b", "Running", "2d",]);
-            table.add_row(row![
-                "llama3-70b",
-                "ollama",
-                "llama3.1:70b",
-                "Downloading",
-                "10s",
-            ]);
 
             table.printstd();
         }
 
         Commands::LS => {
             let mut table = Table::new();
             table.set_format(*format::consts::FORMAT_CLEAN);
-            table.add_row(row!["NAME", "PROVIDER", "REVISION", "SIZE", "CREATED"]);
+            table.add_row(row!["MODEl", "PROVIDER", "REVISION", "SIZE", "CREATED"]);
             table.add_row(row![
                 "deepseek-ai/DeepSeek-R1",
                 "huggingface",
                 "main",
-                "2 weeks ago",
-                "800GB"
+                "80GB",
+                "2 weeks ago"
             ]);
-            table.add_row(row!["llama3.1", "ollama", "8b", "2 weeks ago", "4.9GB"]);
-            table.add_row(row!["llama3.1", "ollama", "70b", "2 weeks ago", "43GB"]);
-            table.add_row(row!["llama3.1", "ollama", "405b", "2 weeks ago", "243GB"]);
             table.printstd();
         }
 
         Commands::PULL(args) => match args.provider {
             Provider::Huggingface => {
                 println!("Downloading model from Huggingface...");
             }
-            Provider::Ollama => {
-                let d = OllamaDownloader::new(&args.model);
-                let model_path = file::root_home().join(file::model_folder_name(&args.model));
-                file::create_folder_if_not_exists(&model_path).unwrap();
-                d.download_model(&model_path).await.unwrap();
-            }
             Provider::Modelscope => {
                 println!("Downloading model from Modelscope...");
             }
         },
 
         Commands::RUN => {
-            println!("Creating and running a new inference service from a model...");
+            println!("Creating and running a new model...");
         }
 
         Commands::STOP => {
-            println!("Stopping one running inference service...");
+            println!("Stopping one running model...");
         }
 
         Commands::RM => {
@@ -132,10 +109,6 @@ pub async fn run(cli: Cli) {
         }
 
         Commands::INSPECT => {
-            println!("Returning detailed information about inference service...");
-        }
-
-        Commands::SHOW => {
             println!("Returning detailed information about model...");
         }
 

src/cli/mod.rs

@@ -1 +1 @@
-pub mod cmds;
+pub mod commands;

src/downloader/mod.rs

@@ -1,2 +1 @@
 mod downloader;
-pub mod ollama;

src/downloader/ollama.rs

@@ -6,13 +6,13 @@ use clap::Parser;
 use env_logger;
 use tokio::runtime::Builder;
 
-use crate::cli::cmds::{run, Cli};
+use crate::cli::commands::{run, Cli};
 use crate::util::file;
 
 fn main() {
     env_logger::init();
 
-    // create the root folder.
+    // Create the root folder if it doesn't exist.
     file::create_folder_if_not_exists(&file::root_home()).unwrap();
 
     let runtime = Builder::new_multi_thread()