Yzma：用 Go 直接调用 llama.cpp 推理引擎的内部实现
在上一篇文章 我们研究了推理的实际情况是——模型如何逐个标记输入提示并构建响应。我提到了两个可以让你本地运行这个循环的Go项目：伊兹玛，使得 Go 称llama.cpp 推理引擎直接，以及克朗克，它会在其上构建一个友好的 SDK。今天我们打开yzma，看看整个过程是如何组合起来的。
评论
点赞
收藏Fake Clocks, Real Guarantees: Inside Go's synctest
The first time I reached for testing/synctest, I assumed it was a sleep helper with better manners. The public API is small enough to support that assumption: synctest.Test(t, func(t *testing.T) {... ...
深入 Linux 内核：虚拟文件系统 (VFS) 原理
Linux内核系列续篇，从调度器深入文件系统层。解析程序打开文件时的内核路径：VFS如何统一不同文件系统接口，以及底层驱动交互机制。适合想补齐操作系统底层知识的开发者。
Go 运行时深度解析：Profiling 机制揭秘
深入解析 Go 运行时五种 Profile（CPU、Heap、Block、Mutex、Goroutine）的底层采集机制与数据格式。文章揭示了它们共享同一 pprof 协议骨架，但采集模型截然不同：CPU 基于信号中断与无锁环形缓冲区流式处理；Heap/Block/Mutex 在分配器或锁内部原地聚合采样；Goroutine 则是全量快照。详细拆解了采样率随机化、延迟计数（GC 配合）、时长加权采样及缩放估算等关键工程细节。
真实Go存储引擎中的MMAP与pread之争
以VictoriaLogs为例，深入剖析Go存储引擎中mmap与pread的性能权衡。指出mmap虽能减少系统调用开销，但冷数据引发的Major Page Fault会导致Go线程阻塞且无法被Runtime调度器感知，从而引发整体停顿。文章展示了结合mincore检查页面驻留状态的双路径读取实现，为高性能Go数据库开发提供了极具价值的底层优化思路。
理解 Linux 内核：调度器
深入解析Linux 7.1内核调度器机制。澄清进程与线程在底层均为task_struct，详解EEVDF算法如何通过虚拟运行时间(vruntime)实现公平性与低延迟平衡。剖析上下文切换的缓存冷启动成本及抢占触发逻辑，适合希望理解操作系统核心原理的开发者。
Understanding the Go Runtime: The Reflect Package
In the previous article we watched the runtime rebuild an entire stack trace out of metadata the compiler and linker had frozen into the binary at build time. I told you at the end that reflect works ...
Memory Manager
In the previous article we looked at how a user program crosses the ring 3 → ring 0 boundary to ask the kernel for help. The example we used was read — a file descriptor, a buffer pointer, a byte cou...
Stacktraces
In the previous article we took apart the select statement and saw how it’s really two features in one, with the compiler rewriting the easy shapes away and only the hard cases falling through to the...
System Calls
In the previous article we followed the kernel from the very first instruction the bootloader handed us all the way to the moment kernel_init called execve on /sbin/init. That was a long ride, but it...
Understanding the Linux Kernel: The Linux Kernel Startup
Have you ever wondered what really happens between the moment you press the power button and the moment your login screen shows up? That gap—usually some seconds—hides one of the most intricate initia...
Understanding the Go Runtime: Slices, Maps, and Channels
So far in this series we’ve looked at the parts of the Go runtime that orchestrate execution — the memory allocator, the scheduler, the garbage collector, sysmon, the netpoller. Today we’re switching ...
Understanding the Go Runtime: The Network Poller
In the previous article we saw how sysmon steps in every 10ms to call netpoll(0) on behalf of busy Ps, making sure network I/O doesn’t stall when the scheduler is too busy to poll on its own. We gloss...
Filesystems: Btrfs
In the previous article, we explored XFS—a filesystem built for extreme scale that divides the disk into independent Allocation Groups, each with its own B+ trees for free space, inodes, and extent tr...
Understanding the Go Runtime: The System Monitor
In the previous articles we explored the scheduler — how goroutines get multiplexed onto OS threads through the GMP model — and the garbage collector — how Go tracks and reclaims memory using a concur...
Understanding the Go Runtime: The Garbage Collector
In the previous article we explored the Go scheduler — how goroutines get multiplexed onto OS threads, the GMP model, and all the tricks the runtime uses to keep your cores busy. But there’s a fundame...