UCB-ADRS / ADRSLinks
AI-Driven Research Systems (ADRS)
β81Updated 3 weeks ago
Alternatives and similar repositories for ADRS
Users that are interested in ADRS are comparing it to the libraries listed below
Sorting:
- π₯ LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilationβ¦β105Updated last month
- Easy, Fast, and Scalable Multimodal AIβ79Updated this week
- An efficient implementation of the NSA (Native Sparse Attention) kernelβ126Updated 5 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decodingβ135Updated last year
- β34Updated 10 months ago
- β32Updated 3 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersβ130Updated last year
- β105Updated 3 months ago
- The evaluation framework for training-free sparse attention in LLMsβ106Updated 2 months ago
- [Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environmentsβ154Updated last month
- Beyond KV Caching: Shared Attention for Efficient LLMsβ20Updated last year
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoningβ56Updated last month
- Memory optimized Mixture of Expertsβ69Updated 4 months ago
- A Practitioner's Guide to M(eow)ti Turn Agentic ReinfOrcement learningβ65Updated 2 weeks ago
- An early research stage expert-parallel load balancer for MoE models based on linear programming.β456Updated 3 weeks ago
- β47Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of codeβ51Updated 5 months ago
- β69Updated 3 weeks ago
- β38Updated last year
- dInfer: An Efficient Inference Framework for Diffusion Language Modelsβ340Updated this week
- Defeating the Training-Inference Mismatch via FP16β163Updated last month
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learningβ54Updated last month
- Compression for Foundation Modelsβ34Updated 4 months ago
- fmchisel: Efficient Compression and Training Algorithms for Foundation Modelsβ76Updated last month
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face supportβ202Updated this week
- Fast and memory-efficient exact attentionβ74Updated 9 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.β212Updated 6 months ago
- β53Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.β52Updated last year
- β56Updated 6 months ago