Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"
☆88Sep 12, 2025Updated 6 months ago
Alternatives and similar repositories for softpick-attention
Users that are interested in softpick-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fork of Flame repo for training of some new stuff in development☆19Mar 17, 2026Updated 2 weeks ago
- Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (N…☆17Apr 13, 2025Updated 11 months ago
- Code for the paper "Cottention: Linear Transformers With Cosine Attention"☆20Nov 15, 2025Updated 4 months ago
- ☆25Oct 31, 2024Updated last year
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆72Jul 8, 2025Updated 8 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Code repository for the paper "MrT5: Dynamic Token Merging for Efficient Byte-level Language Models."☆56Sep 25, 2025Updated 6 months ago
- An Ultra-Long Output Reinforcement Learning Approach☆23Jul 31, 2025Updated 8 months ago
- The evaluation framework for training-free sparse attention in LLMs☆122Jan 27, 2026Updated 2 months ago
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆30Nov 12, 2024Updated last year
- Efficient encoder-decoder architecture for small language models (≤1B parameters) with cross-architecture knowledge distillation and visi…☆32Feb 7, 2025Updated last year
- Universal Neurons in GPT2 Language Models☆30May 28, 2024Updated last year
- Superposition Yields Robust Neural Scaling☆63Feb 12, 2026Updated last month
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆60Mar 17, 2025Updated last year
- Transformer related optimization, including BERT, GPT☆14Jun 27, 2023Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity☆22Aug 28, 2025Updated 7 months ago
- ☆19Nov 5, 2025Updated 4 months ago
- Tiny evaluation of leading LLMs on competitive programming problems☆14Nov 28, 2024Updated last year
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆21Updated this week
- ☆18Apr 8, 2025Updated 11 months ago
- ☆68Mar 21, 2025Updated last year
- Official Implementation of wd1☆24Sep 25, 2025Updated 6 months ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated last year
- ☆33Nov 11, 2024Updated last year
- Wordpress hosting with auto-scaling on Cloudways • AdFully Managed hosting built for WordPress-powered businesses that need reliable, auto-scalable hosting. Cloudways SafeUpdates now available.
- Code for the paper "Function-Space Learning Rates"☆25Jun 3, 2025Updated 9 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Apr 7, 2025Updated 11 months ago
- [ICML2025] KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference☆26Jan 27, 2026Updated 2 months ago
- [AAAI'26] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression☆19Dec 21, 2025Updated 3 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Apr 22, 2025Updated 11 months ago
- ☆275Jun 6, 2025Updated 9 months ago
- Marketplace ML experiment - training without backprop☆27Sep 9, 2025Updated 6 months ago
- ☆18Jan 29, 2026Updated 2 months ago
- An official implementation of Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards☆37Oct 3, 2025Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆43Sep 15, 2025Updated 6 months ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆29Jul 24, 2025Updated 8 months ago
- Code for the paper "On the Expressivity Role of LayerNorm in Transformers' Attention" (Findings of ACL'2023)☆57Sep 27, 2024Updated last year
- CUPTI based GPU profiling library exposing usdt hooks☆28Updated this week
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆160Jul 8, 2025Updated 8 months ago
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆15Apr 30, 2025Updated 11 months ago
- Official Repository of LatentSeek☆80Jun 6, 2025Updated 9 months ago