1 dépôt
Awesome GitHub RepositoriesAlignment Loss Optimizers
Optimized kernels that reduce memory usage during preference alignment fine-tuning by fusing loss computation with linear transformations.
Distinct from Training Memory Optimizers: Distinct from Training Memory Optimizers: focuses specifically on memory reduction for alignment/post-training losses (DPO, ORPO, SimPO, CPO), not general training memory techniques like gradient checkpointing.
Explore 1 awesome GitHub repository matching data & databases · Alignment Loss Optimizers. Refine with filters or upvote what's useful.
Awesome Alignment Loss Optimizers GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- linkedin/liger-kernel
linkedin/Liger-Kernel
6,148Voir sur GitHubLiger-Kernel is a collection of pre-built fused Triton kernels and patching utilities designed to accelerate large language model training. It provides drop-in kernel replacements for common LLM operations such as RMSNorm, cross-entropy loss, and attention, enabling increased throughput and reduced memory usage while preserving bitwise-exact gradients. The project serves as a toolkit for composing custom model architectures from individual optimized kernels and for patching pre-existing models with minimal code changes. The project distinguishes itself through its ability to perform runtime m
Provides fused kernels that cut memory usage by up to 80% during preference alignment fine-tuning.
Pythonfinetuninggemma2hacktoberfest
