giannisanni/

pulsar

GitHub

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.

24stars

2forks

0issues

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

vllm-project/

vllm

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

86k19kPython

hiyouga/

LlamaFactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

73k8.9kPython

ollama/

ollama

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

176k17kGo

huggingface/

transformers

🤗 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.

163k34kPython

lobehub/

lobehub

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

80k16kTypeScript

mindsdb/

mindshub

Make AI do actual work. Swap the model anytime — keep everything you've built.

39k6.2kMakefile

Comparepulsar vs vllm pulsar vs LlamaFactory pulsar vs ollama

SharePost on X LinkedIn