107 skills · sorted by relevance
Estimate inference memory for models on Hugging Face Hub without downloading their weights. Check GPU capacity for Safetensors or GGUF files, with optional estimates for the KV cache, memory used to retain attention data during generation.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
The English summary is being prepared. Showing the original description.
[omh] Self-hosted LLM serving on GPUs: choose the serving engine and quantization from decision tables, prepare deployment as an idempotent runbook with observed-only verification, and measure the endpoint with the standard TTFT/TPOT/goodput protocol. Use when the user says: inference-serving, inference serving, serve this model, serve the model, model serving, serving endpoint, vllm, llama.cpp.
The English summary is being prepared. Showing the original description.
Qdrant vector database with filtering, payloads, and quantization support
The English summary is being prepared. Showing the original description.
Deploy and manage vLLM for high-throughput LLM inference. Configure continuous batching, tensor parallelism, quantization, and OpenAI-compatible API endpoints for production LLM serving.
The English summary is being prepared. Showing the original description.
Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.
The English summary is being prepared. Showing the original description.
Fine-tunes LLMs and trains custom models using LoRA/QLoRA adapters, JSONL training datasets, hyperparameter configuration, RLHF, DPO, and model quantization.
The English summary is being prepared. Showing the original description.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
The English summary is being prepared. Showing the original description.
Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp.
The English summary is being prepared. Showing the original description.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
The English summary is being prepared. Showing the original description.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
The English summary is being prepared. Showing the original description.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
The English summary is being prepared. Showing the original description.
Use bitsandbytes for k-bit PyTorch quantization, Hugging Face quantized model loading, 8-bit and paged optimizers, direct quantized layers/functions, and backend installation diagnostics.
The English summary is being prepared. Showing the original description.
Route Baichuan2 chat inference, deployment/quantization, and fine-tuning workflows.
The English summary is being prepared. Showing the original description.
Route AIMET install, PyTorch/ONNX quantization, GenAILab, model access, cluster/Pod, Qualcomm SDK, optimization, export, and repository tasks to focused operating guidance.
The English summary is being prepared. Showing the original description.
Think and work like an expert Machine Learning Engineer. Use when a task calls for Machine Learning Engineer judgment. Reasons from decision-policy framing, Google's Rules of ML, point-in-time data, and prefill/decode inference physics through GBDT/PyTorch baselines, vLLM/SGLang/KServe serving with FP8/AWQ quantization, hybrid-retrieval RAG, RAGAS and human-validated LLM judges, OpenTelemetry GenAI tracing, and post-Omnibus EU AI Act obligations while treating train-serve skew, temporal leakage, prompt injection, LLM nondeterminism, and degenerate feedback loops as first-class failure modes.
The English summary is being prepared. Showing the original description.
Generate and edit synchronized audio-video with LTX-2.3 using the official hosted LTX API or official local/open-weight LTX-2 repository. Use for text-to-video, image-to-video, audio-to-video, retake, extend, HDR conversion, local inference, checkpoint selection, quantization, and LTX-specific production planning.
The English summary is being prepared. Showing the original description.
Review and adapt vllm_metax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs. Verify registration, inherited state, weight layouts and actual backend selection. Use for registry compatibility work, not standalone attention algorithms or monkey patches.
The English summary is being prepared. Showing the original description.
Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels. Establish quantization and cache differences, preserve upstream structure, and distinguish shared upstream bugs from adaptation defects. Use for model support work, not standalone monkey-patch or registry audits.
The English summary is being prepared. Showing the original description.
Use when reducing model size, improving inference speed, or deploying to edge devices - covers quantization, pruning, knowledge distillation, ONNX export, and TensorRT optimizationUse when ", " mentioned.
The English summary is being prepared. Showing the original description.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
The English summary is being prepared. Showing the original description.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
The English summary is being prepared. Showing the original description.
Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN), store embeddings on nodes or relationships, use SEARCH clause (Neo4j 2026.01+, preferred) or db.index.vector.queryNodes() procedure (deprecated 2026.04, still works on 2025.x), configure HNSW and quantization options, pick similarity function and embedding provider dimensions, and batch-update embeddings. Use when tasks involve CREATE VECTOR INDEX, vector.dimensions, cosine/euclidean search, embedding ingestion pipelines, semantic or structural nearest-neighbor lookup, or hybrid search (vector + fulltext, multiple vector sources, or graph-derived scores). Does NOT handle GraphRAG retrieval_query graph traversal — use neo4j-graphrag-skill. Does NOT handle fulltext-only/keyword-only search — use neo4j-cypher-skill. Does NOT compute GDS graph embeddings (FastRP, Node2Vec) — use neo4j-gds-skill.
The English summary is being prepared. Showing the original description.
LLM serving for latency, batching, caching, quantization, and routing. Use when tuning vLLM or SGLang, sizing KV cache, adding speculative decoding, or cutting serving cost.
The English summary is being prepared. Showing the original description.