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

Name the parity oracle per model family

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Georg BauerandClaude Opus 5.5 committed 2026-10-03 19:10:48 +02:00
1 parent dcc4c516f0
commit 5773942c8f
1 file changed
+5 -2
Download Patch File Download Diff File Expand all files Collapse all files
AGENTS.md
+5 -2
View File
@@ -3,8 +3,11 @@
- Prefer simple, idiomatic Rust; reuse existing code and dependencies before adding abstractions or crates. - Prefer simple, idiomatic Rust; reuse existing code and dependencies before adding abstractions or crates.
- Keep changes focused, handle errors explicitly, and add the smallest useful test for non-trivial behavior. - Keep changes focused, handle errors explicitly, and add the smallest useful test for non-trivial behavior.
- Preserve `rustfmt` output and keep Clippy warning-free. - Preserve `rustfmt` output and keep Clippy warning-free.
- Treat DS4 as the behavioral oracle. Model execution, token processing, context accounting, and KV-cache behavior must remain identical to DS4. Differences are bugs unless they are unavoidable Rust/platform requirements and the user explicitly approves them before implementation; when uncertain, preserve DS4 behavior. - Each model family has one behavioral oracle. Model execution, token processing, sampling/RNG, context accounting, and KV-cache/session behavior must remain identical to it. Differences are bugs unless they are unavoidable Rust/platform requirements and the user explicitly approves them before implementation; when uncertain, preserve the oracle's behavior.
- Keep all application, model-loading, inference-graph, session, and orchestration code in Rust. Never copy, vendor, compile, or call DS4's C implementation; use it only as a behavioral and performance reference. Native code is limited to the Objective-C Metal bridge and `.metal` kernels required to execute GPU work. - DeepSeek and GLM models: DS4.
- Qwen 3.8 Flash Next: the pinned MTPLX revision. Follow its current execution route, not only its numerical results.
- Keep family-specific behavior in that family's code. Before changing a helper shared across families, trace every caller and keep the other families' oracle behavior exact, with regression controls.
- Keep all application, model-loading, inference-graph, session, and orchestration code in Rust. Never copy, vendor, compile, or call DS4's C implementation or MTPLX/MLX Python; use them only as behavioral and performance references. Native code is limited to the Objective-C Metal bridge and `.metal` kernels required to execute GPU work.
- This is not a GitHub project. Use direct `git` commands for version control and the `tea` CLI for forge operations; do not use GitHub tools or workflows. - This is not a GitHub project. Use direct `git` commands for version control and the `tea` CLI for forge operations; do not use GitHub tools or workflows.
- Issues are managed with the command "tea" run from the project directory. - Issues are managed with the command "tea" run from the project directory.