NVlabs / COATLinks
[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
β209Updated last week
Alternatives and similar repositories for COAT
Users that are interested in COAT are comparing it to the libraries listed below
Sorting:
- π₯ A minimal training framework for scaling FLA modelsβ170Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ295Updated 7 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMsβ126Updated last week
- β114Updated 3 weeks ago
- A sparse attention kernel supporting mix sparse patternsβ238Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLMβ163Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.β99Updated 3 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inferenceβ113Updated last month
- β256Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"β137Updated last month
- β130Updated 4 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Trainingβ210Updated 10 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"β233Updated last week
- Efficient triton implementation of Native Sparse Attention.β168Updated last month
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Servingβ310Updated 11 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)β282Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.β127Updated 5 months ago
- 16-fold memory access reduction with nearly no lossβ99Updated 2 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantizationβ136Updated last month
- Code Repository of Evaluating Quantized Large Language Modelsβ124Updated 9 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cacheβ303Updated 5 months ago
- Odysseus: Playground of LLM Sequence Parallelismβ70Updated last year
- β141Updated 3 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ519Updated 3 weeks ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitinβ¦β57Updated 11 months ago
- The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>β134Updated 3 weeks ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationβ359Updated 10 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.β128Updated 2 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Lengthβ89Updated 2 months ago
- slime is a LLM post-training framework aiming at scaling RL.β328Updated this week