Aleph-Alpha-Research / NeurIPS-WANT-submission-efficient-parallelization-layoutsLinks
☆22Updated last year
Alternatives and similar repositories for NeurIPS-WANT-submission-efficient-parallelization-layouts
Users that are interested in NeurIPS-WANT-submission-efficient-parallelization-layouts are comparing it to the libraries listed below
Sorting:
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- GPU operators for sparse tensor operations☆33Updated last year
- ☆39Updated last year
- ☆31Updated last year
- Awesome Triton Resources☆31Updated last month
- ☆20Updated 2 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆48Updated 2 years ago
- Sequence-level 1F1B schedule for LLMs.☆17Updated last year
- Transformers components but in Triton☆34Updated last month
- ☆48Updated last year
- Quantized Attention on GPU☆44Updated 7 months ago
- Linear Attention Sequence Parallelism (LASP)☆84Updated last year
- ☆26Updated 7 months ago
- ☆114Updated 3 weeks ago
- Estimate MFU for DeepSeekV3☆24Updated 5 months ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 4 years ago
- Vocabulary Parallelism☆19Updated 3 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- ☆21Updated 3 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆47Updated 7 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 8 months ago
- ☆39Updated this week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- ☆30Updated last month
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆79Updated 9 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆99Updated 3 weeks ago