Skip to content

Instantly share code, notes, and snippets.

View tommedema's full-sized avatar
🎯
Focusing

Tom Medema tommedema

🎯
Focusing
60 followers · 33 following
View GitHub Profile
@HyperBrain
HyperBrain / lifecycle-cheat-sheet.md
Last active April 9, 2026 05:34
Serverless Lifecycle Cheat Sheet

Serverless plugin author's cheat sheet

This cheat sheet provides a detailed overview of the exposed lifecycle events and available commands (and entrypoints) of the Serverless framework, that can be hooked by plugins (internal and external ones). The document is structured by the commands invoked by the user.

Lifecycle events are shown as the globally available outer events (all providers) and sub lifecycle events that are provider specific in the called order. Currently only the AWS provider is shown. If you have information about the other provider,

@spemer
spemer / customize-scrollbar.css
Last active May 16, 2025 20:21
✨ Customize website's scrollbar like Mac OS. Not supports in Firefox and IE.
/* Customize website's scrollbar like Mac OS
Not supports in Firefox and IE */
/* total width */
body::-webkit-scrollbar {
background-color: #fff;
width: 16px;
}
/* background of the scrollbar except button or resizer */
@andywer
andywer / _readme.md
Last active January 8, 2025 04:42
React - Functional error boundaries

React - Functional error boundaries

Thanks to React hooks you have now happily turned all your classes into functional components.

Wait, all your components? Not quite. There is one thing that can still only be implemented using classes: Error boundaries.

There is just no functional equivalent for componentDidCatch and deriveStateFromError yet.

Proposed solution

@timinar
timinar / GLM-5.2-on-8xA100-vLLM.md
Last active August 21, 2026 23:10
Running GLM-5.2 (753B DeepSeek-Sparse-Attention MoE) on 8x A100 80GB with vLLM — TRITON_MLA_SPARSE backend (PR #38476), no-recompile install, benchmarks

Running GLM-5.2 (753B DSA MoE) on 8× A100 80GB with vLLM

TL;DR. GLM-5.2 (glm_moe_dsa — DeepSeek Sparse Attention) does not run on Ampere (A100, sm_80) with stock vLLM: the sparse-MLA attention backend (FLASHMLA_SPARSE) and the lightning-indexer's fp8_mqa_logits (DeepGEMM) are Hopper/Blackwell-only. vLLM PR #38476 (issue #38006) adds a Triton sparse-MLA backend (TRITON_MLA_SPARSE) + a bf16 Triton indexer fallback that run on Ampere. Cherry-picking it onto current main is a Python-only change — no CUDA recompile. Result: GLM-5.2 AWQ-INT4 serves on 8× A100 at ~56 tok/s single-stream and ~625 tok/s aggregate decode (32-way), with coherent output.

This is an independent 8× A100 confirmation of PR #38476 (the author validated on 32× A100), plus a no-recompile install note. Credit to @haosdent for the PR.

Requirements

  • 8× A100 80GB (sm_80). ~410 GiB VRAM used at TP=8, so all 8 GPUs.