tools to install & use GPU's
  • Rust 69.1%
  • JavaScript 12.7%
  • HTML 8.2%
  • CSS 5.2%
  • Shell 4.8%
Find a file
despiegk 1fb79ee26c
Some checks failed
build / check (push) Failing after 37s
chore: rename herolib_derive to herolib_macros
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-06 21:30:04 +02:00
.forgejo/workflows feat: scaffold hero_gpu workspace with 7 crates 2026-04-26 13:18:48 +02:00
crates chore: rename herolib_derive to herolib_macros 2026-06-06 21:30:04 +02:00
schema feat: add service.toml manifests and OSchema definitions for hero_gpu crates 2026-05-31 22:53:12 +02:00
scripts chore: replace CODEROOT with PATH_CODE in build_lib.sh 2026-05-16 16:22:00 +02:00
.gitignore chore: remove Cargo.lock and update gitignore 2026-06-06 08:05:10 +02:00
Cargo.toml chore: rename herolib_derive to herolib_macros 2026-06-06 21:30:04 +02:00
Cargo.toml.hero_builder_backup chore: migrate hero_rpc deps to hero_blueprint, add hero_rpc2, tune dev profile 2026-05-29 23:00:13 +02:00
README.md refactor: rename HERO_SOCKET_DIR to PATH_SOCKET and drop redundant env vars 2026-05-29 20:43:27 +02:00
rust-toolchain.toml chore: migrate hero_gpu_sdk from hero_blueprint to herolib_openrpc/herolib_derive 2026-06-01 07:44:58 +02:00

hero_gpu

OpenRPC gateway in front of an SGLang Python backend, exposing OpenAI- and Anthropic-compatible endpoints, an installer, an SDK, and an admin UI.

Crates

  • hero_gpu — CLI binary (handles --start / --stop, registers with hero_proc)
  • hero_gpu_server — JSON-RPC server + OpenRPC spec + SGLang client
  • hero_gpu_api — OpenAI + Anthropic HTTP adapters (library)
  • hero_gpu_sdk — generated client from openrpc.json
  • hero_gpu_installer — uv-based sandboxed Python/SGLang installer
  • hero_gpu_ui — Askama + Bootstrap admin dashboard
  • hero_gpu_examples — examples + integration test skeleton

Sockets

All under ~/hero/var/sockets/hero_gpu/:

  • rpc.sock — JSON-RPC 2.0 (consumed by hero_gpu_sdk)
  • openapi.sock — OpenAI + Anthropic compatible HTTP (consumed by external clients)
  • ui.sock — admin dashboard

Quickstart

make install # build + install binaries to ~/hero/bin/
make download-assets # fetch Bootstrap, Icons, Unpoly into hero_gpu_ui/static/
make run # start service via hero_proc
make logs # tail server logs
make stop # stop service

SGLang backend

Launched as a separate hero_proc action via scripts/sglang_runner.sh, running inside a uv-managed Python venv at ~/hero/var/hero_gpu/python/. The Rust server talks to it over 127.0.0.1:30000.

See crates/hero_gpu_server/openrpc.json for the full RPC interface.