Results for “rasm2”

Train, evaluate, export, quantize, and run inference on Mask2Former models for panoptic, instance, and semantic segmentation using NVIDIA TAO.

RF Toolbox and RF Blockset in MATLAB -- S-parameter I/O, network conversions (S/Z/Y/ABCD/T/H/G, mixed-mode), cascade/de-embedding, rfbudget analysis, circuit composition, matching networks, amplifier stability, mixer spurs, rational fitting, SI channels, baseband processing, Circuit Envelope simulation. Trigger: sparameters, Touchstone, .s2p, .s4p, rfplot, smithplot, rfparam, rfwrite, zparameters, yparameters, abcdparameters, s2sdd, cascadesparams, deembedsparams, rfbudget, noise figure, OIP3, IIP3, amplifier, modulator, nport, rffilter, attenuator, seriesRLC, shuntRLC, lcladder, txline, circuit, setports, clone, matchingnetwork, stabilityk, stabilitymu, powergain, gammams, gammaml, mixerIMT, OpenIF, rational, rationalfit, stepresp, txlineWRLGC, rf.Amplifier, rf.Mixer, rf.Filter, rf.Sparameter, rfsystem, RF Blockset.

Evaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Computes the R2Score metric using torchmetrics, handling single and multi-output predictions with options for adjusted and variance-weighted scores.

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and peripheral drivers.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming. Expert in the latest Rust ecosystem including Tokio, axum, and cutting-edge crates. Use PROACTIVELY for Rust development, performance optimization, or systems programming.

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

Expert en Ollama avancé (local LLMs, models, REST API, hardware, multi-modal, DZ deployment)

Backend Rust Specialist IA — Expert en développement backend Rust (Actix, Axum, Tokio, zero-cost abstractions, WASM)

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Custom board bringup for Zephyr RTOS using Hardware Model v2 (HWMv2). Covers directory structure, board.yml metadata, core configuration files (Kconfig, defconfig, CMake), and revision management. Trigger when creating new board definitions or porting Zephyr to custom hardware.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Master Rust 1.75+ development with async runtime (Tokio/smol).