From 74d8bbf9eb15c7d1cc40751f6e436e67d62f6dac Mon Sep 17 00:00:00 2001
From: shyringo <63188642+shyringo@users.noreply.github.com>
Date: Thu, 20 Aug 2026 01:49:15 +0800
Subject: [PATCH] Add deepseek-v4-flash-0731-in-c inference framework
---
README.md | 1 +
1 file changed, 1 insertion(+)
diff --git a/README.md b/README.md
index 2fe67aa..89ed428 100644
--- a/README.md
+++ b/README.md
@@ -196,6 +196,7 @@ python3 download_pdfs.py # The code is generated by Doubao AI
|2025.07|🔥[**siiRL**] DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training(@Shanghai Inovation Institute)|[[pdf]](https://arxiv.org/pdf/2507.13833)|[[siiRL]](https://github.com/sii-research/siiRL)
|⭐️⭐️ |
|2025.04|🔥[**ToolPipe**] ToolPipe: 120+ Free Developer Tools REST API & MCP Server for AI Agents(@COSAI-Labs)|[[docs]](https://toolpipe.dev)|[[toolpipe-mcp-server]](https://github.com/COSAI-Labs/toolpipe-mcp-server) |⭐️ |
|2026.06|🔥[**ANEForge**] ANEForge: Python for direct computation on the Apple Neural Engine(@Georgia Tech)|[[pdf]](https://arxiv.org/pdf/2606.17090)|[[ANEForge]](https://github.com/sbryngelson/ANEForge) |⭐️ |
+|2026.08|🔥[**deepseek-v4-flash-0731-in-c**] DeepSeek-V4-Flash-0731 inference directly from the native checkpoint on laptop CPUs in pure C99(@shyringo)|[[docs]](https://github.com/shyringo/deepseek-v4-flash-0731-in-c/blob/main/docs/DSV4_ARCHITECTURE.md)|[[code]](https://github.com/shyringo/deepseek-v4-flash-0731-in-c) |⭐️ |
### 📖Continuous/In-flight Batching ([©️back👆🏻](#paperlist))