feifeibear / DPSKV3MFULinks
Estimate MFU for DeepSeekV3
☆24Updated 5 months ago
Alternatives and similar repositories for DPSKV3MFU
Users that are interested in DPSKV3MFU are comparing it to the libraries listed below
Sorting:
- ☆49Updated last month
- ☆60Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆99Updated 3 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- ☆21Updated 3 months ago
- Quantized Attention on GPU☆44Updated 7 months ago
- ☆77Updated 2 months ago
- TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators☆59Updated last week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- ☆114Updated 3 weeks ago
- ☆63Updated this week
- A simple calculation for LLM MFU.☆38Updated 3 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated last year
- ☆54Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆113Updated last month
- ☆19Updated 6 months ago
- DeeperGEMM: crazy optimized version☆69Updated last month
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆47Updated 2 weeks ago
- ☆52Updated 6 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆20Updated 8 months ago
- ☆86Updated 3 months ago
- ☆96Updated 9 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆48Updated 3 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated 2 weeks ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆136Updated this week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 3 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆51Updated last year
- ☆104Updated 2 weeks ago