Results for “research-memo”
9 skills
orchestra-research unsloth
Provides expert guidance for fast fine-tuning with Unsloth, including LoRA/QLoRA optimization, with 2-5x faster training and 50-80% less memory usage.
10.4k · bundle
orchestra-research optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
10.4k · bundle
orchestra-research quantizing-models-bitsandbytes
Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.
10.4k · bundle
orchestra-research rwkv-architecture
Use RWKV, a linear-time RNN-Transformer hybrid, for efficient long-context inference and training with constant memory usage.
10.4k · bundle
More results
orchestra-research awq-quantization
Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.
10.4k · bundle
orchestra-research gptq
Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.
10.4k · bundle
orchestra-research ml-training-recipes
Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.
10.4k · bundle
orchestra-research pytorch-fsdp2
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
10.4k · bundle
orchestra-research llama-cpp
Run LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
10.4k · bundle