systems · microsoft
Low-latency inference server built on DeepSpeed-Inference with blocked KV-cache and tensor-parallel model deployment.
| Weight file SHA-256 | f155353f074e6b49530d930e5ed639d5a16d33c4ebe7e6fe20f141740d7ee429 |
|---|
| Publisher | microsoft |
|---|---|
| Origin | United States |
| Licence | Apache-2.0 |
| Pulls recorded here | 29,503 |
Registry record as of 2026-06-06. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.