LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper
•
2312.11514
•
Published
•
252
speed
-
-
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
Paper • 2312.12456 • Published • 40 -
Accelerating LLM Inference with Staged Speculative Decoding
Paper • 2308.04623 • Published • 20 -
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
Paper • 2208.07339 • Published • 4 -
Efficient Memory Management for Large Language Model Serving with PagedAttention
Paper • 2309.06180 • Published • 25 -
Efficient LLM inference solution on Intel GPU
Paper • 2401.05391 • Published • 8 -
DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference
Paper • 2401.08671 • Published • 12 -
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper • 2401.10774 • Published • 50 -
Zero Bubble Pipeline Parallelism
Paper • 2401.10241 • Published • 19 -
Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy
Paper • 2312.12728 • Published -
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
Paper • 2401.15077 • Published • 17 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 62 -
Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models
Paper • 2311.03687 • Published -
Hydragen: High-Throughput LLM Inference with Shared Prefixes
Paper • 2402.05099 • Published • 16 -
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Paper • 2402.02750 • Published • 3 -
TP-Aware Dequantization
Paper • 2402.04925 • Published • 3 -
FAST: Factorizable Attention for Speeding up Transformers
Paper • 2402.07901 • Published • 1 -
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Paper • 2401.18079 • Published • 5 -
CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
Paper • 2404.08763 • Published • 1