LiangrunFlora / Slow-Fast-SamplingLinks
Official PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles" (Slow Fast Sampling).
☆34Updated 3 months ago
Alternatives and similar repositories for Slow-Fast-Sampling
Users that are interested in Slow-Fast-Sampling are comparing it to the libraries listed below
Sorting:
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆103Updated last year
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆80Updated 4 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆86Updated 8 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆174Updated 2 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆88Updated 11 months ago
- [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models☆114Updated 5 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆143Updated 4 months ago
- ☆105Updated last month
- paper list, tutorial, and nano code snippet for Diffusion Large Language Models.☆124Updated 4 months ago
- A Collection of Papers on Diffusion Language Models☆137Updated last month
- TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models☆296Updated 3 weeks ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆132Updated 4 months ago
- Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation, ICML 2024☆21Updated last year
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆39Updated last year
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆97Updated 4 months ago
- ☆61Updated 4 months ago
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆101Updated last month
- ☆10Updated last year
- One-shot Entropy Minimization☆187Updated 4 months ago
- Official Repository: A Comprehensive Benchmark for Logical Reasoning in MLLMs☆43Updated 4 months ago
- V1: Toward Multimodal Reasoning by Designing Auxiliary Task☆36Updated 6 months ago
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆60Updated last month
- The official repository for the paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆56Updated this week
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆67Updated 3 months ago
- Official Repository of LatentSeek☆66Updated 5 months ago
- Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"☆40Updated 4 months ago
- [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More☆61Updated 8 months ago
- Codes for Merging Large Language Models☆33Updated last year
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆41Updated 6 months ago
- Recent Advances on MLLM's Reasoning Ability☆26Updated 6 months ago