Git Stars Git Stars

#tensor-parallelism Repositories

Discover 14 active open source GitHub repositories tagged with #tensor-parallelism, accumulating 45,528 total stars (averaging 3,252 stars per project). Leading this topic is bigscience-workshop/petals with 9,864 stars.

14
Total Repositories
45,528
Total Stars
3,252
Avg Stars/Repo
Programming Languages: Python C++
1
bigscience-workshop/petals

Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

bigscience-workshop
โญ 9,864 Python ๐Ÿ‘ค bigscience-workshop Organization ๐Ÿ• Updated 2024-09-07 ๐Ÿ“… Created 2022-06-12
2
google/gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

google
โญ 7,089 C++ ๐Ÿ‘ค google Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-02-13
3
meta-pytorch/gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

meta-pytorch
โญ 6,244 Python ๐Ÿ‘ค meta-pytorch Organization ๐Ÿ• Updated 2025-08-22 ๐Ÿ“… Created 2023-10-17
4
pytorch/torchtitan

A PyTorch native platform for training generative AI models

pytorch
โญ 5,936 Python ๐Ÿ‘ค pytorch Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-12-13
5
sgl-project/mini-sglang

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

sgl-project
โญ 5,623 Python ๐Ÿ‘ค sgl-project Organization ๐Ÿ• Updated 2026-05-17 ๐Ÿ“… Created 2025-09-01
6
turboderp-org/exllamav3

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

turboderp-org
โญ 1,853 Python ๐Ÿ‘ค turboderp-org Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2025-04-06
7
ByteDance-Seed/Triton-distributed

Distributed Compiler and Optimized Parallel Kernels

ByteDance-Seed
โญ 1,587 Python ๐Ÿ‘ค ByteDance-Seed Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-04-02
8
bigscience-workshop/Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

bigscience-workshop
โญ 1,426 Python ๐Ÿ‘ค bigscience-workshop Organization ๐Ÿ• Updated 2024-03-20 ๐Ÿ“… Created 2021-07-02
9
NVIDIA-NeMo/labs-molt

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

NVIDIA-NeMo
โญ 1,395 Python ๐Ÿ‘ค NVIDIA-NeMo Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-06-23
10
tanishqkumar/beyond-nanogpt

Minimal and annotated implementations of key ideas from modern deep learning research.

tanishqkumar
โญ 1,361 Python ๐Ÿ‘ค tanishqkumar User ๐Ÿ• Updated 2026-01-29 ๐Ÿ“… Created 2025-04-16
โญ 1,323 Python ๐Ÿ‘ค ChenmienTan User ๐Ÿ• Updated 2026-05-20 ๐Ÿ“… Created 2025-04-04
12
MDK8888/GPTFast

Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.

MDK8888
โญ 687 Python ๐Ÿ‘ค MDK8888 User ๐Ÿ• Updated 2024-08-22 ๐Ÿ“… Created 2024-02-18
โญ 553 C++ ๐Ÿ‘ค Tencent Organization ๐Ÿ• Updated 2026-08-27 ๐Ÿ“… Created 2024-05-22

Frequently Asked Questions

1

What is the most popular #tensor-parallelism repository on GitHub?

The top ranked open source #tensor-parallelism project on GitHub is bigscience-workshop/petals with 9,864 stars. Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

2

Which programming languages are most used in #tensor-parallelism repositories?

Among the top ranked #tensor-parallelism projects on GitHub, the most common programming languages are Python, C++.

3

How is the #tensor-parallelism repository ranking calculated?

We track 14 active open source repositories tagged with #tensor-parallelism (500+ stars), totaling 45,528 stars with an average of 3,252 stars per repository. Rankings update daily from the GitHub API.