UCB-ADRS / ADRSLinks
AI-Driven Research Systems (ADRS)
β74Updated this week
Alternatives and similar repositories for ADRS
Users that are interested in ADRS are comparing it to the libraries listed below
Sorting:
- β103Updated 2 months ago
- π₯ LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilationβ¦β99Updated 2 weeks ago
- An efficient implementation of the NSA (Native Sparse Attention) kernelβ126Updated 5 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of codeβ51Updated 4 months ago
- Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoningβ25Updated 2 months ago
- β34Updated 9 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learningβ51Updated 2 weeks ago
- β143Updated last week
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.β50Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decodingβ131Updated 11 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoningβ52Updated 3 weeks ago
- Easy, Fast, and Scalable Multimodal AIβ73Updated this week
- Flash-Muon: An Efficient Implementation of Muon Optimizerβ206Updated 5 months ago
- β55Updated 5 months ago
- β132Updated 5 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM traβ¦β44Updated last month
- The evaluation framework for training-free sparse attention in LLMsβ104Updated last month
- Defeating the Training-Inference Mismatch via FP16β154Updated last week
- Beyond KV Caching: Shared Attention for Efficient LLMsβ20Updated last year
- β254Updated 5 months ago
- β43Updated this week
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Schedulingβ40Updated last month
- β71Updated 3 months ago
- β95Updated 8 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsityβ60Updated 4 months ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cachβ¦β48Updated 3 weeks ago
- β199Updated this week
- Implementation for FP8/INT8 Rollout for RL training without performence drop.β275Updated 2 weeks ago
- Memory optimized Mixture of Expertsβ69Updated 3 months ago
- Fast and memory-efficient exact attentionβ74Updated 8 months ago