NVlabs / COATLinks
[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
☆218Updated last month
Alternatives and similar repositories for COAT
Users that are interested in COAT are comparing it to the libraries listed below
Sorting:
- A sparse attention kernel supporting mix sparse patterns☆262Updated 5 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆307Updated 3 weeks ago
- ☆123Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆211Updated 3 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆124Updated 2 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆140Updated 2 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆136Updated 5 months ago
- Efficient triton implementation of Native Sparse Attention.☆177Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆102Updated 4 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆320Updated this week
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆141Updated 3 weeks ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆212Updated 11 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆127Updated 11 months ago
- ☆268Updated 3 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆106Updated 2 months ago
- 🔥 A minimal training framework for scaling FLA models☆209Updated last month
- The official implementation of the EMNLP 2023 paper LLM-FP4☆211Updated last year
- ☆153Updated 2 years ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆149Updated 2 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆537Updated 2 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆72Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆318Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆101Updated 3 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆395Updated last week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆480Updated 5 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆145Updated 2 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆365Updated 11 months ago
- Code Repository of Evaluating Quantized Large Language Models☆129Updated 10 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆128Updated 5 months ago