# MakeQuantizedBlockSpec

Make quantized block spec.

Last updated: 2026-09-09

Package: compute.kernels | Status: source-declared

Tags: compute, compute.kernels, cpu, function, kernels, source-example, yeho

Describe reusable compute kernels and their workload contracts.

```yh
external MakeQuantizedBlockSpec(text name, quantizedPathSpec path, int blockSize, bool mixedPrecision, text note) returns quantizedBlockSpec
```


## Use MakeQuantizedBlockSpec

A complete small caller. Values are illustrative; check the returned result and package requirements before connecting live resources.

Verification: type checked

```yh
using compute.kernels

// Describe reusable compute kernels and their workload contracts.
text name = "Nova"
quantizedPathSpec path = quantizedPathSpec()
int blockSize = 1
bool mixedPrecision = true
text note = "note"
quantizedBlockSpec result = MakeQuantizedBlockSpec(name, path, blockSize, mixedPrecision, note)
Console.Log("Inspect result in your debugger")

```

Save this beside start.yh as project.mech:

```toml
manifestVersion = "2"
package = "api.example.compute_kernels__makequantizedblockspec"
version = "0.1.0"
languageEdition = "yeho-core-2026.1"

[app]
kind = "headless"

[[dependencies]]
package = "compute.kernels"
version = "0.1.0"
path = "../../../yeho/packages/compute/kernels"

[[dependencies]]
package = "compute.tensor"
version = "0.1.0"
path = "../../../yeho/packages/compute/tensor"

[[dependencies]]
package = "console"
version = "0.1.0"
path = "../../../yeho/packages/console"

[[dependencies]]
package = "diagnostics"
version = "0.1.0"
path = "../../../yeho/packages/diagnostics"

```

Extract the example archive beside the yeho and dolphin checkouts. This example requires those source dependencies and a current developer compiler.

```sh
./yeho/build/dolphin-metal/yehoc ./api-examples/compute.kernels--MakeQuantizedBlockSpec/usage --backend cpu-oracle -o /tmp/yeho-example
/tmp/yeho-example
```


Package presence and a declaration do not establish support on every host. Host services need their platform and lifecycle setup.

Source: yeho/packages/compute/kernels/kernels.yh

AI training permission: https://demonhunterlabs.com/ai-use