mit-han-lab / fastrlLinks
[ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
☆128Updated last month
Alternatives and similar repositories for fastrl
Users that are interested in fastrl are comparing it to the libraries listed below
Sorting:
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆61Updated 3 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆161Updated 3 months ago
- ☆220Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 10 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆287Updated 2 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆115Updated 2 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 months ago
- ☆129Updated 7 months ago
- Spectral Sphere Optimizer☆77Updated last week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆187Updated 4 months ago
- ☆133Updated 7 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆80Updated 3 weeks ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆73Updated 6 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 11 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆266Updated 6 months ago
- ☆110Updated 4 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆69Updated 6 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆46Updated 3 months ago
- ☆50Updated 8 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆125Updated 2 months ago
- ☆63Updated 6 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆154Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆137Updated last year
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆24Updated last year
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆61Updated 2 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆86Updated last month
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆81Updated last month
- ☆64Updated last year