We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 76e5779 commit f65bed4Copy full SHA for f65bed4
api/inference/v1/inference_sdk.go
@@ -286,9 +286,6 @@ type ModelSupportedNode struct {
286
287
// DeploymentQuantization: deployment quantization.
288
type DeploymentQuantization struct {
289
- // Enabled: whether to enable quantization for this deployment.
290
- Enabled bool `json:"enabled"`
291
-
292
// Bits: the number of bits each model parameter should be quantized to. The quantization method is chosen based on this value.
293
Bits uint32 `json:"bits"`
294
}
0 commit comments