From 767f0fce3ac5a0ed0fab48e5a0cbcf87ff6bd514 Mon Sep 17 00:00:00 2001 From: lightseek-bot <243258330+lightseek-bot@users.noreply.github.com> Date: Sat, 27 Jun 2026 20:49:57 +0000 Subject: [PATCH] docs: add blog and talk README link Signed-off-by: lightseek-bot <243258330+lightseek-bot@users.noreply.github.com> --- README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 0b75bea93b..2ed3362373 100644 --- a/README.md +++ b/README.md @@ -20,10 +20,14 @@ Core components: ## News -- [2026/06] Deep dive into the design and optimization of TokenSpeed-Kernel. [[Blog](https://pytorch.org/blog/lightseek-tokenspeed-kernel/)] +- [2026/06] Deep dive into the design and optimization of TokenSpeed-Kernel. [[blog](https://pytorch.org/blog/lightseek-tokenspeed-kernel/)] - [2026/05] 🚀 TokenSpeed hits 580 TPS on Qwen3.5-397B-A17B for agentic workloads. [[blog](https://pytorch.org/blog/up-to-580tps-new-speed-record-of-qwen3-5-397b-a17b-on-gpu-for-agentic-workloads-with-tokenspeed/)] - [2026/05] TokenSpeed announced — a speed-of-light LLM inference engine for agentic workloads. [[blog](https://lightseek.org/blog/lightseek-tokenspeed.html)] +## Blogs and Talks + +For technical blogs, conference talks, and engineering articles from LightSeek Foundation, visit the [LightSeek Blog](https://lightseek.org/blog/). + ## Performance Comparison TokenSpeed vs. TensorRT-LLM Pareto curves on agentic workload (Kimi K2.5, B200)