feat(vllm): Allow to set quantization (#1094)

This particularly useful to set AWQ

**Description**

Follow up of #1015 

**Notes for Reviewers**


**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
 

<!--
Thank you for contributing to LocalAI! 

Contributing Conventions:

1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR. 
3. Sign your commits

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

api/backend/options.go

@@ -44,6 +44,7 @@ func gRPCModelOpts(c config.Config) *pb.ModelOptions {
 		NoMulMatQ:     c.NoMulMatQ,
 		DraftModel:    c.DraftModel,
 		AudioPath:     c.VallE.AudioPath,
+		Quantization:  c.Quantization,
 		LoraAdapter:   c.LoraAdapter,
 		LoraBase:      c.LoraBase,
 		NGQA:          c.NGQA,