Source codes for paper "BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity".
☆20Jan 10, 2026Updated 10 months ago
Alternatives and similar repositories for BlockFFN
Users that are interested in BlockFFN are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Transformers components but in Triton☆35May 9, 2025Updated last year
- ☆37Aug 7, 2025Updated last year
- HRM-MoE: Efficient Sparse Pretraining with Hierarchical Reasoning☆11Jun 17, 2026Updated 5 months ago
- ☆15Jul 10, 2026Updated 4 months ago
- a simple API to use CUPTI☆10Aug 19, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- CUDA Graph runtime tensor debugging utilities for PyTorch☆18Jul 12, 2026Updated 4 months ago
- Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design☆26May 29, 2025Updated last year
- ☆11Apr 5, 2021Updated 5 years ago
- [ACL 2023 Findings] Emergent Modularity in Pre-trained Transformers☆26Jun 7, 2023Updated 3 years ago
- RollPacker: Taming Long-Tail Rollouts for RL Post-Training with Tail Batching☆12Mar 2, 2026Updated 8 months ago
- ☆32Jul 2, 2025Updated last year
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆20Dec 8, 2023Updated 2 years ago
- ☆20Nov 5, 2024Updated 2 years ago
- Debug print operator for cudagraph debugging☆18Aug 2, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆19Mar 7, 2025Updated last year
- Block-GTQ: RoPE-aware bit allocation for KV-cache quantization☆17Oct 29, 2026Updated 2 weeks ago
- This repository contains a simple web application that allows users to generate QR codes for URLs.☆13Apr 25, 2024Updated 2 years ago
- A Feishu/Lark AI agent bot☆16Feb 27, 2026Updated 8 months ago
- Implementation of Sketch Your Own GAN in Jittor☆10Jan 2, 2022Updated 4 years ago
- LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation☆18Oct 15, 2026Updated last month
- [TMLR 2026] LibMoE: A LIBRARY FOR COMPREHENSIVE BENCHMARKING MIXTURE OF EXPERTS IN LARGE LANGUAGE MODELS☆52May 26, 2026Updated 5 months ago
- ☆40Dec 14, 2025Updated 11 months ago
- ☆19Jun 3, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Muon in Int8 Precision Made Possible☆21Nov 7, 2026Updated last week
- ☆14Oct 3, 2024Updated 2 years ago
- Datasets, mainly related to Entity Linking and biological corpus.☆10May 24, 2020Updated 6 years ago
- The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LA…☆30Nov 24, 2024Updated last year
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆68Aug 3, 2025Updated last year
- Sequence-level 1F1B schedule for LLMs.☆37Aug 26, 2025Updated last year
- code for Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning☆20Jul 16, 2024Updated 2 years ago
- Modular Markdown-based audio skills for AI agents and developers, covering signal processing, synthesis, effects, analysis, and spatial a…☆24May 21, 2026Updated 5 months ago
- Code for paper "Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation" (ICLR'24)☆13Nov 17, 2023Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A linker for partial GPU kernels.☆47Oct 28, 2026Updated 3 weeks ago
- FlashSparse significantly reduces the computation redundancy for unstructured sparsity (for SpMM and SDDMM) on Tensor Cores through a Swa…☆41Oct 5, 2025Updated last year
- ☆27Oct 22, 2025Updated last year
- [icml26]Real-Time Vision-Language-Action Control through Streaming Inference☆10Jun 26, 2026Updated 4 months ago
- Implementation of Large Margin aware Focal (LMF) loss☆22Apr 24, 2025Updated last year
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆123Dec 20, 2024Updated last year
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 11 months ago
Are these results useful?