Skills by Orchestra-Research
-
llama-cpp
MIT· ★ 11,165 · updated 2026-06-16 — llama-cpp is a lightweight C/C++ inference engine for running large language models on CPUs and non-NVIDIA hardware, including Apple Silicon and AMD/Intel GPUs. It supports GGUF…
-
tensorrt-llm
MIT· ★ 11,165 · updated 2026-06-16 — TensorRT-LLM accelerates large language model inference on NVIDIA GPUs through advanced optimization techniques including quantization, in-flight batching, and multi-GPU…
-
fine-tuning-with-trl
MIT· ★ 11,165 · updated 2026-06-16 — Fine-tuning with TRL provides post-training methods to align language models with human preferences through multiple approaches. Train models on instruction data with SFT,…
-
serving-llms-vllm
MIT· ★ 11,165 · updated 2026-06-16 — serving-llms-vllm accelerates LLM inference for production environments through PagedAttention-based memory optimization and continuous batching. It supports OpenAI-compatible…