IST-DASLab / MoE-Quant
Code for data-aware compression of DeepSeek models
☆24Updated last month
Alternatives and similar repositories for MoE-Quant
Users that are interested in MoE-Quant are comparing it to the libraries listed below
Sorting:
- Work in progress.☆61Updated last month
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 5 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆41Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- DPO, but faster 🚀☆42Updated 5 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆73Updated 8 months ago
- ☆128Updated 2 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆100Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆161Updated 10 months ago
- ☆54Updated this week
- 16-fold memory access reduction with nearly no loss☆93Updated last month
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆55Updated this week
- ☆131Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆126Updated 5 months ago
- ☆50Updated 6 months ago
- Example of applying CUDA graphs to LLaMA-v2☆12Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆100Updated 3 weeks ago
- KV cache compression for high-throughput LLM inference☆126Updated 3 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 10 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last week
- Load compute kernels from the Hub☆116Updated this week
- Cascade Speculative Drafting☆29Updated last year
- ☆125Updated last year
- QuIP quantization☆52Updated last year
- ☆44Updated last year
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated last year
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆124Updated this week
- Repository for CPU Kernel Generation for LLM Inference☆26Updated last year
- Efficient triton implementation of Native Sparse Attention.☆144Updated last month
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆16Updated 6 months ago