Showing 30 of 27367 results
A Claude skill for designing comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing), enabling systematic test case design with minimal test cases while maintaining high coverage.
Autonomous Claude + Codex review loop. Plan a feature with adversarial pushback, or audit code, all in one window.
Advanced Claude Code framework with 40+ skills, meta-commands, skill orchestration, workflow automation, and TOON format support.
OpenAI-compatible API client integration for vLLM-Omni.
Contributing new models and development workflow for vLLM-Omni.
Distributed inference, disaggregation, and Ray for vLLM-Omni.
Hardware backend guidance for CUDA, ROCm, NPU, and XPU.
Image generation and editing guidance for vLLM-Omni.
End-to-end omni-modality model workflows for vLLM-Omni.
Performance tuning, benchmarking, and acceleration for vLLM-Omni.
Quantization workflows and troubleshooting for vLLM-Omni.
Recipe authoring guidance for omnimodal deployments.
Release note authoring guidance grounded in historical vLLM-Omni releases.
PR review guidelines, checklists, and pitfalls for vLLM-Omni.
Production model serving and API server configuration for vLLM-Omni.
Adding new TTS models and streaming speech serving to vLLM-Omni.
An advanced Claude Code configuration framework with 40+ auto-activating skills (Stripe, Supabase, Expo, Shopify, etc.), meta-commands, skill orchestration, YAML-based workflows, and a TOON format for 30-60% token savings.