Collection by
Feb 20, 2024
Feb 20, 2024
Collections
Discover the best community collections!
Collections including paper arxiv:2402.11131
Collection by
Aug 28, 2024
Aug 28, 2024
-
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 52 -
Simple linear attention language models balance the recall-throughput tradeoff
Paper • 2402.18668 • Published • 18 -
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
Paper • 2402.15220 • Published • 19 -
Linear Transformers are Versatile In-Context Learners
Paper • 2402.14180 • Published • 6
Collection by
Jun 27, 2024
Jun 27, 2024
-
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper • 2401.10774 • Published • 54 -
APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding
Paper • 2401.06761 • Published • 1 -
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
Paper • 2401.02669 • Published • 14 -
MambaByte: Token-free Selective State Space Model
Paper • 2401.13660 • Published • 53
Collection by
May 21, 2024
May 21, 2024
-
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper • 2401.10774 • Published • 54 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 69 -
Speculative Streaming: Fast LLM Inference without Auxiliary Models
Paper • 2402.11131 • Published • 42 -
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
Paper • 2405.11582 • Published • 14
Collection by
Nov 19, 2024
Nov 19, 2024
-
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 145 -
ReFT: Reasoning with Reinforced Fine-Tuning
Paper • 2401.08967 • Published • 29 -
Tuning Language Models by Proxy
Paper • 2401.08565 • Published • 21 -
TrustLLM: Trustworthiness in Large Language Models
Paper • 2401.05561 • Published • 66
Collection by
Jun 25, 2024
Jun 25, 2024
-
FlashDecoding++: Faster Large Language Model Inference on GPUs
Paper • 2311.01282 • Published • 35 -
Co-training and Co-distillation for Quality Improvement and Compression of Language Models
Paper • 2311.02849 • Published • 3 -
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
Paper • 2311.04934 • Published • 28 -
Exponentially Faster Language Modelling
Paper • 2311.10770 • Published • 117
Collection by
16 days ago
16 days ago
-
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
Paper • 2311.04934 • Published • 28 -
Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models
Paper • 2311.08692 • Published • 12 -
Exponentially Faster Language Modelling
Paper • 2311.10770 • Published • 117 -
Memory Augmented Language Models through Mixture of Word Experts
Paper • 2311.10768 • Published • 16
Collection by
Feb 21, 2024
Feb 21, 2024
-
FlashDecoding++: Faster Large Language Model Inference on GPUs
Paper • 2311.01282 • Published • 35 -
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
Paper • 2401.02669 • Published • 14 -
Speculative Streaming: Fast LLM Inference without Auxiliary Models
Paper • 2402.11131 • Published • 42