MayDomine / Seq1F1B
Sequence-level 1F1B schedule for LLMs.
☆17Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for Seq1F1B
- PyTorch bindings for CUTLASS grouped GEMM.☆68Updated 4 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆57Updated 5 months ago
- Distributed IO-aware Attention algorithm☆17Updated 3 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆195Updated 3 months ago
- ☆64Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated 3 weeks ago
- ☆70Updated 2 years ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆41Updated 4 months ago
- ☆79Updated 2 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆104Updated 4 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆219Updated 5 months ago
- ☆188Updated 6 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆46Updated 3 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 11 months ago
- ☆42Updated 6 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆147Updated 4 months ago
- ☆55Updated last week
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- ☆66Updated 3 years ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆202Updated 2 weeks ago
- nnScaler: Compiling DNN models for Parallel Training☆75Updated 3 weeks ago
- Materials for learning SGLang☆105Updated this week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆139Updated 5 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆83Updated 6 months ago
- A sparse attention kernel supporting mix sparse patterns☆58Updated last month
- ☆42Updated 7 months ago
- ☆22Updated 11 months ago