hyhuang00 / moe_inference
Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".
☆16Updated 5 months ago
Alternatives and similar repositories for moe_inference:
Users that are interested in moe_inference are comparing it to the libraries listed below
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆45Updated 4 months ago
- ☆68Updated 2 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆35Updated 3 weeks ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆32Updated last week
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆31Updated this week
- Quantized Attention on GPU☆45Updated 4 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆77Updated 5 months ago
- Implement Flash Attention using Cute.☆74Updated 3 months ago
- ☆55Updated this week
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated last year
- Odysseus: Playground of LLM Sequence Parallelism☆68Updated 9 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆68Updated 2 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆108Updated 10 months ago
- LLM Inference with Microscaling Format☆20Updated 4 months ago
- ☆65Updated 3 months ago
- 16-fold memory access reduction with nearly no loss☆88Updated last week
- AFPQ code implementation☆20Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆25Updated last week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆80Updated this week
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆23Updated last year
- Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆113Updated last week
- ☆91Updated 6 months ago
- ☆53Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆110Updated 3 weeks ago
- Implement some method of LLM KV Cache Sparsity☆30Updated 10 months ago
- GPU operators for sparse tensor operations☆31Updated last year
- ☆38Updated 8 months ago
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆33Updated 6 months ago
- GPTQ inference TVM kernel☆38Updated 11 months ago
- ☆50Updated 2 months ago