mit-han-lab / fastrlLinks
[ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
☆120Updated 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
- ☆213Updated last month
- ☆126Updated 7 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 2 months ago
- ☆62Updated 5 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆282Updated 2 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆110Updated last month
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- ☆109Updated 3 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 10 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆81Updated last month
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆182Updated 3 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆72Updated 5 months ago
- ☆49Updated 7 months ago
- ☆133Updated 7 months ago
- [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.☆52Updated 8 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆64Updated 6 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆43Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆263Updated 6 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆85Updated 5 months ago
- ☆90Updated 6 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆73Updated last week
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆55Updated last year
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆49Updated 5 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆122Updated last month
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆24Updated last year
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆45Updated 2 months ago