hugo/DS4Server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: first cut at actual token generation and model loading

Browse Source
This commit is contained in:
Georg Bauer
2026-07-24 17:44:41 +02:00
parent 616b550849
commit ff984bb96a
38 changed files with 66885 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -1,7 +1,7 @@
# DS4Server
DS4Server is a native macOS coding-agent application for the DwarfStar (`ds4`)
inference engine. It uses Rust and Iced and will combine local model loading, an
DS4Server is a native macOS coding-agent application that rewrites the
DwarfStar (`ds4`) inference engine in Rust. It uses Rust and Iced and will combine local model loading, an
OpenAI-compatible localhost endpoint, and project-scoped agent chat in one app.
The current milestone provides a Codex-inspired project/session layout. A native
@@ -17,6 +17,14 @@ bar. Stopping or quitting keeps the partial file; the next Download/Resume
action continues from that exact byte after relaunch. Exact size and SHA-256
verification happen before an artifact becomes usable.
The selected DeepSeek V4 Flash model can run directly from a project session.
The model, KV/compressor state, 43-layer graph, sampling, and lifecycle are
owned by Rust; a fixed snapshot of the Objective-C Metal boundary and unchanged
Metal kernels is vendored and built inside this repository. Tokens stream into the chat UI, Stop cancels generation,
follow-up turns replay their role history, and the model unloads after the idle
timeout. The current graph supports 2K context while the sparse long-context
indexer and persistent transcript/KV restore remain the next engine slice.
```sh
cargo install cargo-packager --locked --version 0.11.8
make bundle