AbiGMe
Follow
Lists (3)
Agents - RAGs - MCP serv
38 repositories
LLM Inference, Alignment, DPO
plus Preference Tuning + Reward Optimization, high-Throughput, RL, HPO, KV Cache compressions, Reasoning methods, Jailbreaking, TTT n Computation125 repositories
LLM integrations - LAM - GenAI
+ Action LMs, ecosystems, voice features, TTS, Audio54 repositories
Stars
2
stars
written in Cuda
Clear filter
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference