RLsys-Foundation / APRILLinks
APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM training.
☆46Updated 3 months ago
Alternatives and similar repositories for APRIL
Users that are interested in APRIL are comparing it to the libraries listed below
Sorting:
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 11 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
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆128Updated last month
- 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
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆137Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆61Updated 3 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆73Updated 6 months ago
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆13Updated last week
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆80Updated 3 weeks ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆67Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆176Updated last year
- ☆50Updated 8 months ago
- ☆36Updated 11 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 months ago
- ☆84Updated 9 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆113Updated 10 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆161Updated 3 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆79Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆52Updated 5 months ago
- ☆129Updated 7 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆44Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆98Updated 5 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆47Updated last year
- ☆110Updated 4 months ago
- ☆133Updated 7 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆185Updated last week