8000 efsotr / Starred · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View efsotr's full-sized avatar

Block or report efsotr

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Fast and memory-efficient exact attention

Python 4 Updated Jun 2, 2025

Fast Hadamard transform in CUDA, with a PyTorch interface

C 1 Updated Jun 2, 2025

A minimal implementation of Direct Preference Optimization (DPO) in Chinese

Jupyter Notebook 1 Updated May 26, 2025

Just a few lines to combine 🤗 Transformers, Flash Attention 2, and torch.compile — simple, clean, fast ⚡

Python 2 Updated May 24, 2025

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

Python 1,148 76 Updated Jun 26, 2025

Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA

C++ 1,413 82 Updated Jun 27, 2025

SGLang is a fast serving framework for large language models and vision language models.

Python 15,519 2,203 Updated Jun 27, 2025

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Python 6,599 564 Updated Jun 27, 2025

A high-throughput and memory-efficient inference and serving engine for LLMs

Python 50,883 8,371 Updated Jun 27, 2025

Fast and memory-efficient exact attention

Python 18,047 1,772 Updated Jun 25, 2025

GLake: optimizing GPU memory management and IO transmission.

Python 469 41 Updated Mar 24, 2025

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Python 91,076 24,539 Updated Jun 27, 2025

The official repository for our EMNLP 2024 paper, Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability.

Python 20 1 Updated Feb 23, 2025

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Python 146,130 29,470 Updated Jun 27, 2025

State-of-the-art LLM-based translation models.

Ruby 534 42 Updated Apr 9, 2025

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Jupyter Notebook 1,778 279 Updated Dec 27, 2024
0