deepspeed Guide

Name: deepspeed
Author: davila7

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

27,615 starsby davila7

When to use deepspeed

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

How to use deepspeed

deepspeed is a Claude skill in the SKILL.md format. Add it to your Claude environment from the source repository below, then it activates as a user-invocable skill when your task matches its description.

Skill source

https://raw.githubusercontent.com/davila7/claude-code-templates/main/cli-tool/components/skills/ai-research/distributed-training-deepspeed/SKILL.md

Details

PlatformClaude

CategoryFrontend & Web

Invocationuser-invocable

Modelany

Maintainerdavila7

LicenseMIT

deepspeed Guide

When to use deepspeed

How to use deepspeed

Details

Resources