mirror of
https://github.com/Mesh-LLM/mesh-llm.git
synced 2026-08-08 22:23:19 -04:00
Update all michaelneale/mesh-llm references to Mesh-LLM/mesh-llm
Repo was transferred to the Mesh-LLM org. Update all GitHub URLs, install script defaults, auto-update endpoints, CLI defaults, UI links, docs site links, and container image references. Intentionally left alone: - michaelneale/llama.cpp (fork not transferred) - relay.michaelneale.mesh-llm.iroh.link (iroh relay domain, not a GitHub ref)
This commit is contained in:
Michael Neale
parent
a7ddbad834
commit
8b385ebce4
11 changed files with 34 additions and 34 deletions
|
|
@ -168,9 +168,9 @@ These plugins should validate:
|
|||
|
||||
The llama pluginization work should move the current local llama-style serving path behind the new plugin-hosted inference endpoint contract.
|
||||
|
||||
The MLX plugin should then take inspiration from the in-process inference-server work in [PR #103](https://github.com/michaelneale/mesh-llm/pull/103), but implemented using the new plugin endpoint registration architecture rather than direct built-in runtime ownership in core.
|
||||
The MLX plugin should then take inspiration from the in-process inference-server work in [PR #103](https://github.com/Mesh-LLM/mesh-llm/pull/103), but implemented using the new plugin endpoint registration architecture rather than direct built-in runtime ownership in core.
|
||||
|
||||
After that, add an attached external inference plugin, with Lemonade as the first target for that mode. That should take inspiration from [PR #150](https://github.com/michaelneale/mesh-llm/pull/150), but implemented using endpoint registration rather than ad hoc `inference/register` notifications in the transport layer.
|
||||
After that, add an attached external inference plugin, with Lemonade as the first target for that mode. That should take inspiration from [PR #150](https://github.com/Mesh-LLM/mesh-llm/pull/150), but implemented using endpoint registration rather than ad hoc `inference/register` notifications in the transport layer.
|
||||
|
||||
### Phase 9: Host-Owned Plugin Crypto API
|
||||
|
||||
|
|
@ -252,7 +252,7 @@ The pluginized llama backend should prove that the current built-in serving path
|
|||
|
||||
The MLX plugin should then prove that a second plugin-hosted backend can use the same contract while owning its own runtime behavior.
|
||||
|
||||
Take implementation cues from the current llama runtime behavior first, and then from [PR #103](https://github.com/michaelneale/mesh-llm/pull/103):
|
||||
Take implementation cues from the current llama runtime behavior first, and then from [PR #103](https://github.com/Mesh-LLM/mesh-llm/pull/103):
|
||||
|
||||
- plugin-hosted local model serving with llama semantics
|
||||
- plugin-hosted local inference serving
|
||||
|
|
|
|||
10
README.md
10
README.md
|
|
@ -24,7 +24,7 @@ If a model fits on one machine, it runs there. If it does not, Mesh LLM automati
|
|||
Install the latest release:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh | bash
|
||||
curl -fsSL https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh | bash
|
||||
```
|
||||
|
||||
Then start a node:
|
||||
|
|
@ -82,7 +82,7 @@ This starts serving a model, opens the local API and console, and prints an invi
|
|||
### 3. Build from source
|
||||
|
||||
```bash
|
||||
git clone https://github.com/michaelneale/mesh-llm
|
||||
git clone https://github.com/Mesh-LLM/mesh-llm
|
||||
cd mesh-llm
|
||||
just build
|
||||
```
|
||||
|
|
@ -250,7 +250,7 @@ Does not start the console or bind any ports. Use the CLI flags shown in `--help
|
|||
To install it as a per-user background service:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh | bash -s -- --service
|
||||
curl -fsSL https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh | bash -s -- --service
|
||||
```
|
||||
|
||||
Service installs are user-scoped:
|
||||
|
|
@ -434,7 +434,7 @@ The installer currently targets macOS and Linux release bundles. Windows coming
|
|||
To force a specific bundled flavor during install:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh | MESH_LLM_INSTALL_FLAVOR=vulkan bash
|
||||
curl -fsSL https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh | MESH_LLM_INSTALL_FLAVOR=vulkan bash
|
||||
```
|
||||
|
||||
Installed release bundles use flavor-specific llama.cpp binaries:
|
||||
|
|
@ -457,7 +457,7 @@ mesh-llm update --version v0.X.Y
|
|||
If you build from source, always use `just`:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/michaelneale/mesh-llm
|
||||
git clone https://github.com/Mesh-LLM/mesh-llm
|
||||
cd mesh-llm
|
||||
just build
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Issue #115 Spec Compliance Tracker
|
||||
|
||||
**Issue**: https://github.com/michaelneale/mesh-llm/issues/115
|
||||
**Issue**: https://github.com/Mesh-LLM/mesh-llm/issues/115
|
||||
|
||||
This file is the human-readable counterpart to `.github/workflows/docker-precheck.yml`. Both must agree. If they disagree, the reusable workflow is authoritative.
|
||||
|
||||
|
|
|
|||
|
|
@ -9,13 +9,13 @@ For command-by-command CLI usage, model resolution rules, and JSON automation ex
|
|||
Install the latest release bundle:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh | bash
|
||||
curl -fsSL https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh | bash
|
||||
```
|
||||
|
||||
To opt into the latest published prerelease bundle instead:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh | bash -s -- --pre-release
|
||||
curl -fsSL https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh | bash -s -- --pre-release
|
||||
```
|
||||
|
||||
The installer probes your machine, recommends a flavor, and asks what to install.
|
||||
|
|
@ -23,7 +23,7 @@ The installer probes your machine, recommends a flavor, and asks what to install
|
|||
For a non-interactive install, set the flavor explicitly:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh | MESH_LLM_INSTALL_FLAVOR=vulkan bash
|
||||
curl -fsSL https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh | MESH_LLM_INSTALL_FLAVOR=vulkan bash
|
||||
```
|
||||
|
||||
Release bundles install flavor-specific llama.cpp binaries:
|
||||
|
|
@ -43,7 +43,7 @@ mesh-llm serve --llama-flavor vulkan --model Qwen2.5-32B
|
|||
Source builds must use `just`:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/michaelneale/mesh-llm
|
||||
git clone https://github.com/Mesh-LLM/mesh-llm
|
||||
cd mesh-llm
|
||||
just build
|
||||
```
|
||||
|
|
@ -83,7 +83,7 @@ Bare `mesh-llm serve` loads startup models from `[[models]]` in `~/.mesh-llm/con
|
|||
To install Mesh LLM as a per-user background service:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh | bash -s -- --service
|
||||
curl -fsSL https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh | bash -s -- --service
|
||||
```
|
||||
|
||||
Service installs are user-scoped:
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@
|
|||
<a href="#agents">Agents</a>
|
||||
<a href="#blackboard">Blackboard</a>
|
||||
<a href="#features">Features</a>
|
||||
<a href="https://github.com/michaelneale/mesh-llm">GitHub</a>
|
||||
<a href="https://github.com/Mesh-LLM/mesh-llm">GitHub</a>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
|
|
@ -71,7 +71,7 @@
|
|||
<p>Turn spare capacity into an auto-configured p2p inference cloud. Serve many models, access your private models from anywhere, or share compute with others, let your agents collaborate p2p.</p>
|
||||
<div class="hero-ctas">
|
||||
<a href="https://www.anarchai.org/dashboard" class="btn btn-primary">Try it now</a>
|
||||
<a href="https://github.com/michaelneale/mesh-llm" class="btn btn-secondary">View on GitHub</a>
|
||||
<a href="https://github.com/Mesh-LLM/mesh-llm" class="btn btn-secondary">View on GitHub</a>
|
||||
</div>
|
||||
|
||||
<div class="mesh-demo">
|
||||
|
|
@ -195,9 +195,9 @@
|
|||
|
||||
<div class="code-block">
|
||||
<span class="comment"># Install on macOS (downloads ~18MB bundle)</span><br>
|
||||
<span class="cmd">curl</span> <span class="flag">-fsSL</span> <span class="val">https://github.com/michaelneale/mesh-llm/releases/latest/download/mesh-bundle.tar.gz</span> | <span class="cmd">tar</span> xz && mkdir -p ~/.local/bin && mv mesh-bundle/* ~/.local/bin/<br><br>
|
||||
<span class="cmd">curl</span> <span class="flag">-fsSL</span> <span class="val">https://github.com/Mesh-LLM/mesh-llm/releases/latest/download/mesh-bundle.tar.gz</span> | <span class="cmd">tar</span> xz && mkdir -p ~/.local/bin && mv mesh-bundle/* ~/.local/bin/<br><br>
|
||||
<span class="comment"># Install on Linux (build from source — needs just, cmake, nvcc, Rust, Node.js)</span><br>
|
||||
<span class="cmd">git clone</span> <span class="val">https://github.com/michaelneale/mesh-llm</span> && <span class="cmd">cd</span> mesh-llm && <span class="cmd">just</span> build<br><br>
|
||||
<span class="cmd">git clone</span> <span class="val">https://github.com/Mesh-LLM/mesh-llm</span> && <span class="cmd">cd</span> mesh-llm && <span class="cmd">just</span> build<br><br>
|
||||
<span class="comment"># Join the public mesh — instant chat, zero config</span><br>
|
||||
<span class="cmd">mesh-llm</span> <span class="flag">--auto</span><br><br>
|
||||
<span class="comment"># Or start your own mesh with a model</span><br>
|
||||
|
|
@ -396,8 +396,8 @@
|
|||
<div class="cta-buttons">
|
||||
<a href="https://www.anarchai.org/dashboard" class="btn btn-primary">Try it now</a>
|
||||
<a href="#install" class="btn btn-secondary">Install</a>
|
||||
<a href="https://github.com/michaelneale/mesh-llm" class="btn btn-secondary">GitHub →</a>
|
||||
<a href="https://github.com/michaelneale/mesh-llm/blob/main/ROADMAP.md" class="btn btn-secondary">Roadmap</a>
|
||||
<a href="https://github.com/Mesh-LLM/mesh-llm" class="btn btn-secondary">GitHub →</a>
|
||||
<a href="https://github.com/Mesh-LLM/mesh-llm/blob/main/ROADMAP.md" class="btn btn-secondary">Roadmap</a>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
|
@ -409,7 +409,7 @@
|
|||
<li><a href="https://arxiv.org/pdf/2601.16863" style="color:#646cff;">Mixture of Models / NSED</a> — self-evaluating deliberation across models (Peeramid Labs)</li>
|
||||
<li><a href="https://nvidianews.nvidia.com/news/nvidia-launches-nemotron-coalition-of-leading-global-ai-labs-to-advance-open-frontier-models" style="color:#646cff;">NVIDIA Nemotron Coalition</a> — advancing open frontier models across leading AI labs</li>
|
||||
</ul>
|
||||
<p>For current plans and work items, see the <a href="https://github.com/michaelneale/mesh-llm/blob/main/ROADMAP.md" style="color:#646cff;">Roadmap</a> and <a href="https://github.com/michaelneale/mesh-llm/blob/main/mesh-llm/TODO.md" style="color:#646cff;">TODO</a> on GitHub.</p>
|
||||
<p>For current plans and work items, see the <a href="https://github.com/Mesh-LLM/mesh-llm/blob/main/ROADMAP.md" style="color:#646cff;">Roadmap</a> and <a href="https://github.com/Mesh-LLM/mesh-llm/blob/main/mesh-llm/TODO.md" style="color:#646cff;">TODO</a> on GitHub.</p>
|
||||
<p style="margin-top:0.8rem;">Come say hi on <a href="https://github.com/block/goose?tab=readme-ov-file#goose-around-with-us" style="color:#646cff;">Discord</a> — we're in the goose community.</p>
|
||||
</section>
|
||||
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
#
|
||||
# If you modify this file, also update docker/Dockerfile.client and vice versa.
|
||||
# They should be structurally identical to avoid drift between the Fly deploy
|
||||
# and the published ghcr.io/michaelneale/mesh-llm:client image.
|
||||
# and the published ghcr.io/mesh-llm/mesh-llm:client image.
|
||||
#
|
||||
# Deploy:
|
||||
# fly deploy --config fly/console/fly.toml --dockerfile fly/Dockerfile
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
set -euo pipefail
|
||||
|
||||
REPO="${MESH_LLM_INSTALL_REPO:-michaelneale/mesh-llm}"
|
||||
REPO="${MESH_LLM_INSTALL_REPO:-Mesh-LLM/mesh-llm}"
|
||||
REPO_REF="${MESH_LLM_INSTALL_REF:-main}"
|
||||
INSTALL_DIR="${MESH_LLM_INSTALL_DIR:-$HOME/.local/bin}"
|
||||
INSTALL_FLAVOR="${MESH_LLM_INSTALL_FLAVOR:-}"
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ pub(crate) async fn run_blackboard(
|
|||
eprintln!(" Join a mesh: mesh-llm client --join <token>");
|
||||
eprintln!(" Public mesh: mesh-llm client --auto");
|
||||
eprintln!();
|
||||
eprintln!("See https://github.com/michaelneale/mesh-llm for setup guide.");
|
||||
eprintln!("See https://github.com/Mesh-LLM/mesh-llm for setup guide.");
|
||||
std::process::exit(1);
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -96,7 +96,7 @@ pub(crate) struct HfJobArgs {
|
|||
#[arg(long)]
|
||||
pub(crate) hf_job_namespace: Option<String>,
|
||||
/// GitHub repo that hosts the mesh-llm release bundle used by the remote job.
|
||||
#[arg(long, default_value = "michaelneale/mesh-llm")]
|
||||
#[arg(long, default_value = "Mesh-LLM/mesh-llm")]
|
||||
pub(crate) hf_job_release_repo: String,
|
||||
/// Release tag to download inside the remote job. Use `latest` for the latest GitHub release.
|
||||
#[arg(long, default_value = "latest")]
|
||||
|
|
|
|||
|
|
@ -10,11 +10,11 @@ use crate::cli::{Cli, Command};
|
|||
use crate::inference::launch;
|
||||
use crate::VERSION;
|
||||
|
||||
const DEFAULT_RELEASE_REPO: &str = "michaelneale/mesh-llm";
|
||||
const DEFAULT_RELEASE_REPO: &str = "Mesh-LLM/mesh-llm";
|
||||
#[cfg(not(windows))]
|
||||
const INSTALL_SCRIPT_URL: &str =
|
||||
"https://raw.githubusercontent.com/michaelneale/mesh-llm/main/install.sh";
|
||||
const RELEASES_URL: &str = "https://github.com/michaelneale/mesh-llm/releases/latest";
|
||||
"https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/install.sh";
|
||||
const RELEASES_URL: &str = "https://github.com/Mesh-LLM/mesh-llm/releases/latest";
|
||||
const SELF_UPDATE_ATTEMPTED_ENV: &str = "MESH_LLM_SELF_UPDATE_ATTEMPTED";
|
||||
const SELF_UPDATE_REPO_ENV: &str = "MESH_LLM_SELF_UPDATE_REPO";
|
||||
|
||||
|
|
@ -1103,7 +1103,7 @@ mod tests {
|
|||
std::env::remove_var(SELF_UPDATE_REPO_ENV);
|
||||
assert_eq!(
|
||||
release_asset_url("v0.60.0", "mesh-llm-aarch64-apple-darwin.tar.gz"),
|
||||
"https://github.com/michaelneale/mesh-llm/releases/download/v0.60.0/mesh-llm-aarch64-apple-darwin.tar.gz"
|
||||
"https://github.com/Mesh-LLM/mesh-llm/releases/download/v0.60.0/mesh-llm-aarch64-apple-darwin.tar.gz"
|
||||
);
|
||||
}
|
||||
|
||||
|
|
@ -1111,10 +1111,10 @@ mod tests {
|
|||
#[serial]
|
||||
fn test_release_repo_defaults_to_main_repo() {
|
||||
std::env::remove_var(SELF_UPDATE_REPO_ENV);
|
||||
assert_eq!(release_repo(), "michaelneale/mesh-llm");
|
||||
assert_eq!(release_repo(), "Mesh-LLM/mesh-llm");
|
||||
assert_eq!(
|
||||
latest_release_api_url(),
|
||||
"https://api.github.com/repos/michaelneale/mesh-llm/releases/latest"
|
||||
"https://api.github.com/repos/Mesh-LLM/mesh-llm/releases/latest"
|
||||
);
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -2394,7 +2394,7 @@ export function App() {
|
|||
<>
|
||||
<span>·</span>
|
||||
<a
|
||||
href="https://github.com/michaelneale/mesh-llm/releases"
|
||||
href="https://github.com/Mesh-LLM/mesh-llm/releases"
|
||||
target="_blank"
|
||||
rel="noreferrer"
|
||||
className="underline-offset-2 hover:text-foreground hover:underline"
|
||||
|
|
@ -2408,7 +2408,7 @@ export function App() {
|
|||
) : null}
|
||||
<span>·</span>
|
||||
<a
|
||||
href="https://github.com/michaelneale/mesh-llm"
|
||||
href="https://github.com/Mesh-LLM/mesh-llm"
|
||||
target="_blank"
|
||||
rel="noreferrer"
|
||||
className="inline-flex h-5 w-5 items-center justify-center hover:text-foreground"
|
||||
|
|
@ -4634,7 +4634,7 @@ function DashboardPage({
|
|||
</a>
|
||||
{" · "}
|
||||
<a
|
||||
href="https://github.com/michaelneale/mesh-llm"
|
||||
href="https://github.com/Mesh-LLM/mesh-llm"
|
||||
target="_blank"
|
||||
rel="noopener noreferrer"
|
||||
className="inline-flex items-center gap-1 underline hover:text-foreground"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue