tsinghua-ideal / TwilightLinks
Adaptive Attention Sparsity with Hierarchical Top-p Pruning
☆18Updated 4 months ago
Alternatives and similar repositories for Twilight
Users that are interested in Twilight are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆40Updated 6 months ago
- Implement some method of LLM KV Cache Sparsity☆32Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆39Updated last year
- ☆14Updated last year
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆20Updated 8 months ago
- ☆54Updated last year
- Code release for AdapMoE accepted by ICCAD 2024☆26Updated 2 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆9Updated last year
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆48Updated 7 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆48Updated 3 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆79Updated 5 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated 10 months ago
- ☆15Updated 3 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆28Updated 4 months ago
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆24Updated last week
- ☆14Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆90Updated 2 months ago
- Multi-Candidate Speculative Decoding☆35Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 8 months ago
- An experimentation platform for LLM inference optimisation☆31Updated 9 months ago
- More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression☆11Updated 5 months ago
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆24Updated 2 months ago
- ☆30Updated last month
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆17Updated 4 months ago
- ☆42Updated 7 months ago
- LLM Inference with Microscaling Format☆23Updated 7 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆49Updated 2 weeks ago
- ☆52Updated 6 months ago