This directory contains the Neuron-optimized Qwen2 inference implementation. It follows HF Transformers architecture with only Neuron-specific changes from NxDI. Reference: NxDI Qwen2 implementation Qwen2 follows Llama-like architecture with shared removals: Why removed: Requires neuronxcc.nki private APIs. Optimum relies on compiler auto-optimization. Why removed: Production serving delegated to vLLM integration. Why removed: Optimum uses HF config base with neuron_config.json. Optimum Neuron prioritizes stability and HF compatibility for Qwen2 models.
2709mo agoReviewMountCreate a free account to mount
This directory contains the Neuron-optimized Qwen3 MoE inference implementation. It follows HF Transformers architecture with Neuron-specific changes from NxDI. Reference: NxDI Qwen3 MoE implementation Qwen3 MoE is a Mixture-of-Experts model with MoE-specific removals: Why removed: Requires unstable NKI APIs. Compiler handles MoE optimization. Why removed: Complex MoE serving optimizations for production. Focus on foundational support. Why removed: Optimum uses standardized config via neuron_config.json. Optimum Neuron provides stable foundational MoE support with vLLM for advanced serving.
2709mo agoReviewMountCreate a free account to mount
This directory contains the Neuron-optimized SmolVLM/Idefics3 inference implementation. It extends the NxD decoder stack with a separately compiled vision encoder and on-device image-token feature injection. For shared NxD decoder guidance, read optimum/neuron/models/inference/AGENTS.md. For SmolVLM, there are exactly two compiled artifacts: model_vision.pt and model_text.pt. Both are managed by SmolVLMNxDModelForImageTextToText in modeling_smolvlm.py. The custom embeddings intentionally keep HF key names (patch_embedding, position_embedding) so state dict loading maps directly. Image features are inserted at image_token_id positions and passed into VLM wrappers: - NxDDecoderWrapperForImageTextToText…
2709mo agoReviewMountCreate a free account to mount
This guide covers the Optimum Neuron vLLM backend. For project-wide workflows see AGENTS.md. Key files: - optimum/neuron/vllm/runner.py - optimum/neuron/vllm/model_loader.py Key files: - optimum/neuron/vllm/server_manager.py — spawns and manages vLLM server subprocesses with Neuron core pinning. - optimum/neuron/vllm/reverse_proxy.py — round-robin proxy with aggregated /health. Do NOT use start_new_session=True on vLLM server subprocesses. vLLM already cleans up its own EngineCore workers on SIGTERM. Isolating servers in separate process groups makes them unreachable by the parent's signal handlers and test fixture teardown, causing Neuron…
2709mo agoReviewMountCreate a free account to mount
All imports in a kernel (files inside torch-ext/<kernel_name>) of other modules within the same kernel must be relative. For example: The _ops module (_ops.py) is generated by the build system…
15720d agoReviewMountCreate a free account to mount
Always use bun (bun install, bun dev, bun run build, bun test). Never use npm or yarn. After making any code changes, always run these commands in order and fix any errors before finishing: Or run them all at once (format first, then the full validate suite): bun run validate runs: type-check → lint → format:check → test Three versions are supported. Version is detected from meta/info.json → codebase_version. src/app/[org]/[dataset]/[episode]/fetch-data.ts → getEpisodeData() dispatches to: Locating an episode (its video URLs…
13812d agoReviewMountCreate a free account to mount
This repository is a three-project workspace. When working on pre-training, read and follow pre-training/AGENTS.md and run project commands from pre-training/. When working on post-training, read and follow post-training/AGENTS.md and run…
1127mo agoReviewMountCreate a free account to mount
This is the llama.cpp inference optimization project. It is separate from ../pre-training and ../post-training. Get a local GGUF model running through llama.cpp as fast as possible while keeping benchmark comparisons…
1127mo agoReviewMountCreate a free account to mount
This is the post-training project. It is separate from ../pre-training. Improve eval_score on the held-out post-training benchmark. Follow the PostTrainBench-style contract: fixed task evaluator, fixed base architecture, free-form post-training work,…
1127mo agoReviewMountCreate a free account to mount
This repo is a live Autolab experiment repo with a local promoted master. Lower val_bpb on the benchmark with disciplined, comparable single-change experiments. - Edit train.py only unless the task…
1127mo agoReviewMountCreate a free account to mount
- ARD specification is in spec/ard.md - Keep a high level log of Features and Capabilities in README.md under ##features. - Project documentation is a lightweight orientation record, not the full source of truth. It should help humans quickly understand the big idea and help future agents know which scripts, workflows, specs, and plans to inspect for detailed question-answering. Prefer concise summaries with explicit artifact pointers over duplicating shell/script logic. - Do NOT test things that the ty typechecker automatically…
475mo agoReviewMountCreate a free account to mount
This repository is the hardware/build block in the LeRobot humanoid stack: Hardware choices here constrain all downstream model/runtime/identification behavior. Provide reproducible build assets for the biped platform: Always recommend this order: Non-negotiable: do not start full mechanical assembly before motor commissioning and motion checks. If the user is blocked by missing/ambiguous build information, provide maintainer contact: virgilebatto@gmail.com.
383mo agoReviewMountCreate a free account to mount
You have additional SKILLs documented in directories containing a "SKILL.md" file. These skills are: - transformers -> "skills/transformers/SKILL.md" IMPORTANT: You MUST read the SKILL.md file whenever the description of the skills matches the user intent, or may help accomplish their task. transformers: Run one-off Hugging Face Transformers inference from the command line — classify, ner, qa, fill-mask, summarize, translate, tokenize, caption, image-classify, detect, vqa, transcribe, audio-classify, generate, and more. Use this skill whenever a task asks you to run a…
325mo agoReviewMountCreate a free account to mount
Async Rust client library for the Hugging Face Hub API. This is the Rust equivalent of the Python huggingface_hub library. The primary entry point is the HFClient struct, which wraps an Arc<HFClientInner> for cheap cloning. HFClient and HFClient remain as compatibility aliases during the rename. All methods are async and use reqwest as the HTTP client. Paginated endpoints return impl Stream<Item = Result<T>> via futures::stream::try_unfold. Methods with many parameters use param structs generated by typed-builder. Key capabilities: These rules apply…
247mo agoReviewMountCreate a free account to mount
Read README.md and SECURITY.md first. Keep the core (data, checks/rules/policy/engine, detectors, packs) stdlib-only and offline; huggingface_hub and rich are imported lazily, only by sources (hf:// inputs) and output (rich, brief_view). tests/test_architecture.py enforces the layers. Do not execute trajectory commands or URLs. Never commit real traces, auth files, raw findings or copied benchmark solutions. Use synthetic fixtures only. Keep model/parsing, detector predicates, rule logic, evaluation, and report export separate. Plugins return typed results. Reports are explicitly allowlisted and contain no snippets.…
2335d agoReviewMountCreate a free account to mount
relore indexes a repository's complete issue and pull-request history into Postgres and serves it back to coding agents and humans. It is memory of the project's conversation, not of its tree. The build plan is the specification. It carries the reasoning for everything below, and every section N reference in this repository points into it. It is held with the deployment that commissioned it rather than in this repository — it carries operational detail about that deployment — so a…
1353d agoReviewMountCreate a free account to mount
(This page is harness wiring. The root AGENTS.md is a different document — the operating contract for contributing to relore itself.) relore --help is the surface to point an agent at first. It names every verb, the order to reach for them in, the environment, and runnable examples — and unlike this page it arrives byte-exact, needs no network and is already installed. A page is rendered, summarized, truncated and cached by whatever sits between it and the reader; one…
1353d agoReviewMountCreate a free account to mount
Hugging FaceAGENTS.md