TokenSpeed

mentions 3 type Organization feed RSS

// recent coverage 3 mentions

02:51

2026-08-15

dev.to

large-language-models

A beginner's guide to the Qwen3.8-27b model by Qwen on Huggingface

Qwen has released Qwen3.8-27B, a 27-billion-parameter multimodal language model with integrated vision capabilities, built on the Qwen3.5 architecture. The model supports native image and video unders…

22:36

2026-07-26

github.com

large-language-models

Shepherd Model Gateway – Model-routing gateway for LLM deployments

LightSeek Org released Shepherd Model Gateway (SMG), an engine-agnostic, high-performance model-routing gateway for large-scale LLM deployments that centralizes worker lifecycle management and balance…

15:39

2026-05-27

pytorch.org

large-language-models

Up to 580tps! New Speed Record of Qwen3.5-397B-A17B on GPU for Agentic Workloads with TokenSpeed

TokenSpeed, an open-source inference engine, achieved a record-breaking 580 tokens per second running the Qwen3.5-397B-A17B model on GPUs. The performance gain for agentic workloads comes from elimina…

// co-occurs with top 8 entities

Qwen 2 vLLM 2 SGLang 2 Qwen3.5-397B-A17B 1 GPU 1 Hugging Face 1 SWE-bench 1 OSWorld 1

// topics top 6 topics

large language models 3 ai tools 3 ai infrastructure 2 ai agents 1 artificial intelligence 1 ai research 1