apple / ml-cross-entropyLinks
β519Updated last month
Alternatives and similar repositories for ml-cross-entropy
Users that are interested in ml-cross-entropy are comparing it to the libraries listed below
Sorting:
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ538Updated 4 months ago
- Large Context Attentionβ736Updated 7 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β265Updated last month
- Helpful tools and examples for working with flex-attentionβ970Updated last week
- Load compute kernels from the Hubβ283Updated this week
- β638Updated last week
- π₯ A minimal training framework for scaling FLA modelsβ247Updated last week
- Efficient LLM Inference over Long Sequencesβ391Updated 2 months ago
- LLM KV cache compression made easyβ609Updated this week
- Normalized Transformer (nGPT)β188Updated 10 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsβ¦β343Updated 9 months ago
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β856Updated 6 months ago
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ404Updated 10 months ago
- Ring attention implementation with flash attentionβ866Updated last week
- β302Updated 4 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024β335Updated 4 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β576Updated last month
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β436Updated 4 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Headsβ490Updated 7 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"β245Updated 7 months ago
- Scalable toolkit for efficient model reinforcementβ868Updated this week
- Efficient triton implementation of Native Sparse Attention.β218Updated 3 months ago
- A family of compressed models obtained via pruning and knowledge distillationβ351Updated 10 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.β274Updated last month
- β196Updated 9 months ago
- [ICLR2025 Spotlightπ₯] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parametersβ572Updated 7 months ago
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paperβ744Updated last month
- Scalable and Performant Data Loadingβ302Updated this week
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAIβ290Updated 3 months ago
- This repository contains the experimental PyTorch native float8 training UXβ224Updated last year