nex-agi / NexGAPLinks
Nex General Agentic Data Pipeline, an end-to-end pipeline for generating high-quality agentic training data.
☆30Updated 2 months ago
Alternatives and similar repositories for NexGAP
Users that are interested in NexGAP are comparing it to the libraries listed below
Sorting:
- ☆104Updated 2 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆289Updated 3 months ago
- NexRL is an ultra-loosely-coupled LLM post-training framework.☆97Updated last week
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆193Updated this week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆331Updated 9 months ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆353Updated last month
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆61Updated 4 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆54Updated 10 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆40Updated last year
- SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts☆63Updated 2 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Updated last month
- A set of examples based on verl for end-to-end RL training recipes.☆166Updated this week
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆55Updated last year
- [ICLR 2025🔥] D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models☆27Updated 7 months ago
- (best/better) practices of megatron on veRL and tuning guide☆129Updated 4 months ago
- ☆74Updated 10 months ago
- ☆120Updated last week
- ☆129Updated 8 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆269Updated last week
- Repository of LV-Eval Benchmark☆73Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆214Updated last year
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆116Updated 6 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- Async pipelined version of Verl☆124Updated 10 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆47Updated 4 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆131Updated 2 months ago
- Official implementation of "DPad: Efficient Diffusion Language Models with Suffix Dropout"☆55Updated 2 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆197Updated 2 months ago
- a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation☆61Updated 10 months ago
- ☆46Updated 4 months ago