-
NaN Propagation and Constant Bloat in a Flash Attention Compilation Path
A post-mortem of two independent failures in one compiled Flash Attention model – NaN from -inf minus -inf in the online softmax rescale, and a causal mask materialised twenty-four times – traced through the export, tuning, CSE, constant-pool and runtime stages, each of which made one copy.
-
Agent Foundry: A Repository Contract for Agentic Development
How Agent Foundry turns reusable skills, project profiles, session checks and executable policy into a development workflow that can survive a change of agent or session.
-
The Value Boundary of Specialised Operators for High-Performance Transformer Inference in Modern AI Compiler Stacks
An examination of how much value remains in specialised HPC kernel engineering for Transformer inference once modern AI compiler stacks – TVM Relax, TorchInductor, CUTLASS/CuTe and Triton – have absorbed conventional optimisations, assessed through compiler capability boundaries, hardware utilisation, Roofline and Amdahl reasoning, and service-level SLOs.
-
Building a Dual-Stack WireGuard Full-Tunnel Gateway with Dynamic Multi-Network Routing
A complete Hetzner and macOS deployment guide for dual-stack WireGuard egress, private recursive DNS, Apple On-Demand connections, and dynamic routing between an office network, Feilian, and a home LAN.
-
Deploying a Static Service to a Fresh Server: Nginx, Cloudflare, GitHub Actions, and WireGuard
A practical deployment pattern for a fresh Ubuntu server: atomic static-site releases owned by a deploy user, Cloudflare Full (strict), GitHub Actions over restricted SSH, and the firewall rules a WireGuard gateway must retain.
-
The Machine of Innocence in Love
On Moral Laundering, Techniques of Withdrawal, and the Liquidation of Personhood in Modern Intimacy.
-
Building a Stable macOS Remote Development Infrastructure with Tailscale, ShadowRocket, SMB, SSH, and Screen Sharing
A systematic macOS remote-development guide covering how to separate private networking from internet proxying, so that Tailscale, SMB, SSH, and Screen Sharing remain stable while GitHub, Google, Hugging Face, PyPI, and Homebrew stay accelerated.
-
当时只道是寻常
一次与父亲、祖父同行的江南短途旅行,在归家后的空虚中显出真正分量:它记录的不是风景,而是三代人尚能共同远行的短暂时间窗口。
-
Building the MLC-LLM Compilation Stack from Source on NVIDIA H800
A step-by-step technical guide for establishing a complete, source-built machine learning compilation environment on an NVIDIA H800 system under Kubernetes – covering container configuration, read-only filesystem remediation, LLVM and CUDA toolchain installation, and TVM compilation.
-
From Relay to Relax to Unity: The Historical Evolution of Apache TVM’s High-Level Compilation Stack
A deep-dive into Apache TVM’s compiler architecture evolution – from the NNVM graph era through Relay’s graph IR, to Relax’s symbolic-shape-aware dataflow IR and TensorIR integration, culminating in the Unity modular cross-layer ML compilation system.
-
Systematic Analysis and Engineering Solution for Slow SSH Connections (Terminal + VSCode)
A layered diagnosis of slow SSH logins and VSCode Remote-SSH stalls, showing why repeated session setup dominates latency and how ControlMaster-based multiplexing fixes it.
-
When Love Degenerates into Valuation
A philosophical analysis of love, personhood, and instrumental rationality, contrasting fidelity that continues to include the other with valuation that discards them once a better world appears.
-
I Do Not Love Life; I Am Merely, For the Moment, Unable to Win
A Cold Self-Statement on Failure, Self-Defence, Value Camouflage, and Personality Split.
-
Rethinking My First Love
A reflective essay on first love, mutual harm, narrative authority, and the collapse of a shared future under diverging moral and existential doctrines.
-
LLM Inference on Edge Platforms
A systems-level analysis of prefill, decode, KV-cache layout, prefix reuse, and the memory-bandwidth economics that govern practical LLM inference on edge hardware.
-
Performative Learning under Modern Instrumental Rationality
This essay analyses performative learning as a structurally induced response to modern regimes of instrumental rationality. It identifies a status-sensitive subtype whose behaviour is shaped by ambition, externalised self-worth, and acute responsiveness to rank differentials.
-
Cognitive Stratification and Individual Development
A sociological reconstruction of individual development through a four-stage model: institutional screening, linguistic leverage, abstract logic, and holistic self-actualisation – synthesising Bourdieu’s cultural capital with cognitive psychology.
-
The Counterfeit of the Sublime
Using Yu Xiaoqing as a sociopsychological specimen, this analysis dissects the pathology of Performative Idealism – the sophisticated egoist who camouflages instrumental rationality beneath an aestheticised moral shell.
-
Killing Processes in K8s Pods
In Kubernetes pods, processes may appear in ps -ef output but fail to respond to kill commands. This occurs when the target process runs in a different PID namespace. The solution uses nsenter to enter the target namespace and send signals using the container-local PID.
-
On Conditional Recognition and Existential Seeing: The Economics of Love
An exploration of how intimate relationships become arenas of social discipline, where love is conditioned on conformity to externally imposed success metrics – and what it means to resist this through existential seeing.
-
In-depth Analysis of the US Stock Market on 20 November 2025
On 20 November 2025, the US stock market experienced a dramatic open-high, close-low reversal triggered by Nvidia earnings, AI investment anxiety, and shifting Fed rate expectations – the S&P 500’s most severe intraday reversal since April.