> ## Content Index
> Fetch the complete content index at: https://orbiorbi.com/news/llms.txt
> Use this file to discover other available public pages before exploring further.

# llama.cpp b11721 融合 CUDA 运算链
- URL: https://orbiorbi.com/news/hot/llama-cpp-b11721-cuda-hc-post-fusion/
- Published: 2026-10-18T18:08:15.000Z
- Updated: 2026-10-18T23:00:39.000Z
- Description: 据 ggml 发布说明，llama.cpp b11721 将 qwen4exp 的 SCALE、SIGMOID、SCALE 与 hc_post 运算链融合，原先四个内核的处理改为一个内核执行。该实现移植了 Vulkan 的 HC_POST_GATE 融合方案。
- Author: Orbis News
- Tags: #orbis-hot

据 ggml 发布说明，llama.cpp b11721 将 qwen4exp 的 SCALE、SIGMOID、SCALE 与 hc\_post 运算链融合，原先四个内核的处理改为一个内核执行。该实现移植了 Vulkan 的 HC\_POST\_GATE 融合方案。

## 来源与原文

- \[1\] ggml · 2026-10-19 · [查看原文](https://github.com/ggml-org/llama.cpp/releases/tag/b11721?ref=orbiorbi.com)  
版本说明描述将 qwen4exp 的 HC\_POST 运算链融合为一个 CUDA 内核。

{"version":2,"hot":{"event\_id":"llama-cpp-b11721-cuda-hc-post-fusion","group":"open-source","count":1,"heat":20,"verified":"confirmed","firstSeen":"2026-10-18T18:08:15.000Z","lastSeen":"2026-10-18T23:00:30.415Z","sources":\[{"n":"ggml","publisher":"ggml","u":"https://github.com/ggml-org/llama.cpp/releases/tag/b11721","say":"版本说明描述将 qwen4exp 的 HC\_POST 运算链融合为一个 CUDA 内核。","tier":"T0","at":"2026-10-18T18:08:15.000Z"}\],"signals":\[\],"facts":\[\]}}