@tuned-tensor/cli 0.26.2 → 0.27.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +8 -0
- package/dist/index.js +239 -103
- package/dist/index.js.map +1 -1
- package/docs/local-runtime/decision.md +2 -1
- package/docs/local-runtime/hosting.md +121 -0
- package/package.json +1 -1
- package/training/serving/uv.lock +3 -3
package/README.md
CHANGED
|
@@ -861,3 +861,11 @@ the remaining steps toward the full conversational product promise.
|
|
|
861
861
|
## License
|
|
862
862
|
|
|
863
863
|
Apache-2.0
|
|
864
|
+
|
|
865
|
+
## Serverless decision inference
|
|
866
|
+
|
|
867
|
+
`tt cloud endpoints` uploads complete local Laya decision checkpoints to an
|
|
868
|
+
authenticated CPU endpoint, with per-request prepaid billing. See the
|
|
869
|
+
[hosting guide](docs/local-runtime/hosting.md) for creation, inference keys,
|
|
870
|
+
retry-safe requests, costs and deletion. Hosting requires the new server API;
|
|
871
|
+
GPU and adapter checkpoints remain outside this serverless flow.
|