MayDomine / Seq1F1BLinks
Sequence-level 1F1B schedule for LLMs.
☆17Updated last year
Alternatives and similar repositories for Seq1F1B
Users that are interested in Seq1F1B are comparing it to the libraries listed below
Sorting:
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆212Updated 11 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆102Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆106Updated 2 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆123Updated 8 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- Odysseus: Playground of LLM Sequence Parallelism☆72Updated last year
- ☆78Updated 3 months ago
- 16-fold memory access reduction with nearly no loss☆103Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆134Updated 3 weeks ago
- ☆60Updated 3 months ago
- Estimate MFU for DeepSeekV3☆25Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 4 months ago
- ☆145Updated 5 months ago
- Distributed IO-aware Attention algorithm☆21Updated 11 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆67Updated this week
- ☆92Updated 4 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆103Updated 3 months ago
- A simple calculation for LLM MFU.☆42Updated 5 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆54Updated last year
- ☆42Updated last year
- ☆209Updated this week
- GPU operators for sparse tensor operations☆33Updated last year
- ☆86Updated 3 years ago
- ☆96Updated 10 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆198Updated 5 months ago
- Vocabulary Parallelism☆19Updated 4 months ago
- ☆137Updated 5 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆318Updated last year