sail-sg / VocabularyParallelismLinks
Vocabulary Parallelism
☆19Updated 4 months ago
Alternatives and similar repositories for VocabularyParallelism
Users that are interested in VocabularyParallelism are comparing it to the libraries listed below
Sorting:
- Odysseus: Playground of LLM Sequence Parallelism☆72Updated last year
- ☆123Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆123Updated 8 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆42Updated last month
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆108Updated last month
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆48Updated 9 months ago
- Transformers components but in Triton☆34Updated 2 months ago
- ☆20Updated 3 months ago
- ☆78Updated 3 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 4 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆212Updated 11 months ago
- ☆50Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆106Updated 2 months ago
- Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.☆41Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- Estimate MFU for DeepSeekV3☆25Updated 6 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- ☆12Updated 10 months ago
- 16-fold memory access reduction with nearly no loss☆102Updated 4 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 9 months ago
- Quantized Attention on GPU☆44Updated 8 months ago
- KV cache compression for high-throughput LLM inference☆134Updated 6 months ago
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- Hydragen: High-Throughput LLM Inference with Shared Prefixes☆41Updated last year
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆67Updated this week
- Sequence-level 1F1B schedule for LLMs.☆17Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated last month