efficient-inference

10 projets partagent ce topic GitHub

Les traits relient les membres réellement apparentés entre eux. La taille des points suit les étoiles.

🧬 Membres

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

EfficientFormer

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

Awesome-Quantization-Papers

List of papers related to neural network quantization in recent AI conferences and journals.

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

Fast, lossless LLM inference via dual-view diffusion decoding.

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Awesome-Generation-Acceleration

📚 Collection of awesome generation acceleration resources.

On-device LLM Inference Powered by X-Bit Quantization

speculative-decoding

Explorations into some recent techniques surrounding speculative decoding

🔗 Familles voisines

model-compression 19 quantization 51 llama2 56 localllm 5 small-models 4 text-generation 32 compression 22 mistral 66

Mesuré à partir des topics GitHub communs aux deux projets, pondérés par leur rareté.