UNITES-Lab / HEXA-MoELinks
Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"
☆15Updated 10 months ago
Alternatives and similar repositories for HEXA-MoE
Users that are interested in HEXA-MoE are comparing it to the libraries listed below
Sorting:
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆65Updated 6 months ago
- [NAACL'25 🏆 SAC Award] Official code for "Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert…☆13Updated 11 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆47Updated last year
- ☆39Updated 5 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆121Updated last month
- [Archived] For the latest updates and community contribution, please visit: https://gitcode.com/Ascend/TransferQueue☆12Updated this week
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆25Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆74Updated last month
- ☆20Updated last year
- ☆84Updated 8 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆43Updated last year
- Quantized Attention on GPU☆44Updated last year
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆83Updated last month
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆112Updated 2 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆45Updated 3 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆50Updated 5 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- Debug print operator for cudagraph debugging☆14Updated last year
- AFPQ code implementation☆23Updated 2 years ago
- ☆65Updated 8 months ago
- ☆52Updated 7 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 6 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆184Updated 3 months ago
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆39Updated this week
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 3 months ago
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆55Updated last year
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆39Updated last month