Add/refresh how‑to docs and example loader for deployment, Docker, HuggingFace token, and getting‑started tutorials.

docs/howtos/deploy_on_server.md

@@ -25,7 +25,7 @@ housing an NVIDIA GPU, run the following:
 
 ```
 cd examples
-bazel run -c opt //llama:OpenLLaMA-3B --@zml//runtimes:cuda=true
+bazel run --config=release //llama:OpenLLaMA-3B --@zml//runtimes:cuda=true
 ```
 
 
@@ -42,7 +42,7 @@ As an example, here is how you build above OpenLLama for CUDA on Linux X86_64:
 
 ```
 cd examples
-bazel build -c opt //llama:OpenLLaMA-3B               \
+bazel build --config=release //llama:OpenLLaMA-3B               \
             --@zml//runtimes:cuda=true                \
             --@zml//runtimes:cpu=false                \
             --platforms=@zml//platforms:linux_amd64
@@ -84,7 +84,7 @@ tar(
 
 ```
 # cd examples
-bazel build -c opt //mnist:archive                    \
+bazel build --config=release //mnist:archive                    \
             --@zml//runtimes:cuda=true                \
             --@zml//runtimes:cpu=false                \
             --platforms=@zml//platforms:linux_amd64

docs/howtos/dockerize_models.md

@@ -134,7 +134,7 @@ And that's almost it! You can already build the image:
 
 ```
 # cd examples
-bazel build -c opt //simple_layer:image
+bazel build --config=release //simple_layer:image
 
 INFO: Analyzed target //simple_layer:image (1 packages loaded, 8 targets configured).
 INFO: Found 1 target...
@@ -169,7 +169,7 @@ oci_load(
 ... then we can load the image and run it with the following commands:
 
 ```
-bazel run -c opt //simple_layer:load
+bazel run --config=release //simple_layer:load
 docker run --rm distroless/simple_layer:latest
 ```
 
@@ -194,7 +194,7 @@ This will push the `simple_layer` image with the tag `latest` (you can add more)
 to the docker registry:
 
 ```
-bazel run -c opt //simple_layer:push
+bazel run --config=release //simple_layer:push
 ```
 
 When dealing with maybe a public and a private container registry - or if you
@@ -202,7 +202,7 @@ just want to try it out **right now**, you can always override the repository on
 the command line:
 
 ```
-bazel run -c opt //simple_layer:push -- --repository my.server.com/org/image
+bazel run --config=release //simple_layer:push -- --repository my.server.com/org/image
 ```
 
 
@@ -216,7 +216,7 @@ We'll use the [MNIST
 example](https://github.com/zml/zml/tree/master/examples/mnist) to illustrate
 how to build Docker images that also contain data files.
 
-You can `bazel run -c opt //mnist:push -- --repository
+You can `bazel run --config=release //mnist:push -- --repository
 index.docker.io/my_org/zml_mnist` in the `./examples` folder if you want to try
 it out.
 
@@ -232,7 +232,7 @@ platforms your containerized model should support.**
 **Example:**
 
 ```
-bazel run //mnist:push -c opt --@zml//runtimes:cuda=true -- --repository index.docker.io/my_org/zml_mnist
+bazel run //mnist:push --config=release --@zml//runtimes:cuda=true -- --repository index.docker.io/my_org/zml_mnist
 ```
 
 

docs/howtos/huggingface_access_token.md

@@ -34,8 +34,8 @@ Now you're ready to download a gated model like `Meta-Llama-3-8b`!
 # requires token in $HOME/.cache/huggingface/token, as created by the
 # `huggingface-cli login` command, or the `HUGGINGFACE_TOKEN` environment variable.
 cd examples
-bazel run -c opt //llama:Meta-Llama-3-8b
-bazel run -c opt //llama:Meta-Llama-3-8b -- --promt="Once upon a time,"
+bazel run --config=release //llama:Meta-Llama-3-8b
+bazel run --config=release //llama:Meta-Llama-3-8b -- --promt="Once upon a time,"
 ```
 
 

docs/huggingface-access-token.md

@@ -31,7 +31,7 @@ Now you're ready to download a gated model like `Meta-Llama-3-8b`!
 # requires token in $HOME/.cache/huggingface/token, as created by the
 # `huggingface-cli login` command, or the `HUGGINGFACE_TOKEN` environment variable.
 cd examples
-bazel run -c opt //llama:Meta-Llama-3-8b
-bazel run -c opt //llama:Meta-Llama-3-8b -- --promt="Once upon a time,"
+bazel run --config=release //llama:Meta-Llama-3-8b
+bazel run --config=release //llama:Meta-Llama-3-8b -- --promt="Once upon a time,"
 ```
 

docs/tutorials/getting_started.md

@@ -50,7 +50,7 @@ On the command line:
 
 ```
 cd examples
-bazel run -c opt //mnist
+bazel run --config=release //mnist
 ```
 
 ### Llama
@@ -75,8 +75,8 @@ Once you've been granted access, you're ready to download a gated model like
 # requires token in $HOME/.cache/huggingface/token, as created by the
 # `huggingface-cli login` command, or the `HUGGINGFACE_TOKEN` environment variable.
 cd examples
-bazel run -c opt //llama:Llama-3.1-8B-Instruct
-bazel run -c opt //llama:Llama-3.1-8B-Instruct -- --prompt="What is the capital of France?"
+bazel run --config=release //llama:Llama-3.1-8B-Instruct
+bazel run --config=release //llama:Llama-3.1-8B-Instruct -- --prompt="What is the capital of France?"
 ```
 
 You can also try `Llama-3.1-70B-Instruct` if you have enough memory.
@@ -88,8 +88,8 @@ Like the 8B model above, this model also requires approval. See
 
 ```
 cd examples
-bazel run -c opt //llama:Llama-3.2-1B-Instruct
-bazel run -c opt //llama:Llama-3.2-1B-Instruct -- --prompt="What is the capital of France?"
+bazel run --config=release //llama:Llama-3.2-1B-Instruct
+bazel run --config=release //llama:Llama-3.2-1B-Instruct -- --prompt="What is the capital of France?"
 ```
 
 For a larger 3.2 model, you can also try `Llama-3.2-3B-Instruct`.
@@ -120,7 +120,7 @@ run the following:
 
 ```
 cd examples
-bazel run -c opt //llama:Llama-3.2-1B-Instruct            \
+bazel run --config=release //llama:Llama-3.2-1B-Instruct            \
           --@zml//runtimes:cuda=true                      \
           -- --prompt="What is the capital of France?"
 ```

docs/tutorials/write_first_model.md

@@ -380,9 +380,9 @@ const asynk = @import("async");
 With everything in place now, running the model is easy:
 
 ```
-# run release (-c opt)
+# run release (--config=release)
 cd examples
-bazel run -c opt //simple_layer
+bazel run --config=release //simple_layer
 
 # compile and run debug version
 bazel run //simple_layer
@@ -391,7 +391,7 @@ bazel run //simple_layer
 And voila! Here's the output:
 
 ```
-bazel run -c opt //simple_layer
+bazel run --config=release //simple_layer
 INFO: Analyzed target //simple_layer:simple_layer (0 packages loaded, 0 targets configured).
 INFO: Found 1 target...
 Target //simple_layer:simple_layer up-to-date:

examples/loader/main.zig

@@ -24,7 +24,7 @@ pub fn asyncMain() !void {
         break :blk path;
     } else {
         std.debug.print("Missing file path argument\n", .{});
-        std.debug.print("Try: bazel run -c opt //loader:safetensors -- /path/to/mymodel.safetensors or /path/to/model.safetensors.index.json \n", .{});
+        std.debug.print("Try: bazel run --config=release //loader:safetensors -- /path/to/mymodel.safetensors or /path/to/model.safetensors.index.json \n", .{});
         std.process.exit(0);
     };