{"data":{"slug":"deepspeed","etype":"software","name":"DeepSpeed","cat":"Training","subtitle":"Microsoft's scaling toolkit — ZeRO sharding made huge models trainable.","summary":"DeepSpeed's ZeRO optimizer sharding let models far larger than one GPU's memory train efficiently, powering the Megatron-Turing era and countless open efforts since. Its ideas (now echoed by PyTorch FSDP) defined how the industry splits models across thousands of devices.","attrs":null,"kf":{"maker":"Microsoft","license":"Apache 2.0"},"aliases":["ZeRO"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":"Active","region":null,"asof":"2026-01-15","sources":[{"url":"https://www.deepspeed.ai/","label":"DeepSpeed"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T04:29:53+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}