*   Post-training quantization tool supports quantizing weights shared by
        multiple operations. The models made with versions of this tool will use
        INT8 types for weights and will only be executable interpreters from
        this version onwards.
    *   Post-training quantization tool supports fp16 weights and GPU delegate
        acceleration for fp16.
    *   Add delegate support for `QUANTIZED_16BIT_LSTM`.

natively within Kubernetes, without exposing an HTTP endpoint or
using an extra executable.

### Kubelet Credential Provider Graduates to Beta

Originally released as Alpha in Kubernetes 1.20, the kubelet's support for

* Fix link in "Deployment" to "Bigger Applications".

## 0.8.0

* Make development scripts executable. PR [#76](https://github.com/tiangolo/fastapi/pull/76) by [@euri10](https://github.com/euri10).

///

Alternativamente, o HTTPS poderia ser tratado por um provedor de nuvem como um de seus serviços (enquanto ainda executasse o aplicativo em um contêiner).

## Executando na inicialização e reinicializações { #running-on-startup-and-restarts }

Normalmente, outra ferramenta é responsável por **iniciar e executar** seu contêiner.

- Changed buildmode of non static Kubernetes binaries to produce position independent executables (PIE). ([#102323](https://github.com/kubernetes/kubernetes/pull/102323), [@saschagrunert](https://github.com/saschagrunert))
- Clarified the description of a test in the e2e suite that mentions "SCTP" but is