← 返回专题广场

efficient-inference

9 个项目 · ⭐ 5.0k
1
SqueezeAILab
SqueezeAILab/LLMCompiler

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Python ⭐ 1.9k ⑂ 136 MIT · 2024-07-10推送
efficient-inferencefunction-calling
2024-07-10
最近推送
2
snap-research
snap-research/EfficientFormer

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
Python ⭐ 1.1k ⑂ 95 NOASSERTION · 2023-08-13推送
deep-learningdetection
2023-08-13
最近推送
3
horseee
horseee/DeepCache

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
Python ⭐ 970 ⑂ 52 Apache-2.0 · 2024-06-27推送
diffusion-modelsefficient-inference
2024-06-27
最近推送
4
Picovoice
Picovoice/picollm

On-device LLM Inference Powered by X-Bit Quantization
Python ⭐ 317 ⑂ 26 Apache-2.0 · 11 天前推送
compressionefficient-inference
11 天前
最近推送
5
lucidrains
lucidrains/speculative-decoding

Explorations into some recent techniques surrounding speculative decoding
Python ⭐ 307 ⑂ 24 MIT · 2024-12-23推送
artificial-intelligencedeep-learning
2024-12-23
最近推送
6
czg1225
czg1225/AsyncDiff

[NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Python ⭐ 214 ⑂ 13 Apache-2.0 · 2025-09-27推送
diffusion-modelsdistributed-computing
2025-09-27
最近推送
7
InternScience
InternScience/AdaptiveDiffusion

[NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Python ⭐ 73 ⑂ 6 Apache-2.0 · 2025-01-23推送
diffusion-modelsefficient-inference
2025-01-23
最近推送
8
NVlabs
NVlabs/RocketKV

[ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
Python ⭐ 51 ⑂ 10 NOASSERTION · 2025-08-07推送
efficient-inferencelarge-language-models
2025-08-07
最近推送
9
cvsp-lab
cvsp-lab/AgilePruner

[ICLR 2026] AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
Python ⭐ 28 ⑂ 3 Apache-2.0 · 11 天前推送
attentionefficient-inference
11 天前
最近推送