Rename inline -> local (#24)

* Rename the "inline" distribution to "local"

* further rename

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

llama_toolchain/cli/distribution/install.py

@@ -36,7 +36,7 @@ class DistributionInstall(Subcommand):
         self.parser.add_argument(
             "--spec",
             type=str,
-            help="Distribution spec to install (try ollama-inline)",
+            help="Distribution spec to install (try local-ollama)",
             required=True,
             choices=[d.spec_id for d in available_distribution_specs()],
         )

llama_toolchain/data/default_inference_config.yaml

@@ -1,14 +0,0 @@
-inference_config:
-  impl_config:
-    impl_type: "inline"
-    checkpoint_config:
-      checkpoint:
-        checkpoint_type: "pytorch"
-        checkpoint_dir: {checkpoint_dir}/
-        tokenizer_path: {checkpoint_dir}/tokenizer.model
-        model_parallel_size: {model_parallel_size}
-        quantization_format: bf16
-    quantization: null
-    torch_seed: null
-    max_seq_len: 16384
-    max_batch_size: 1

llama_toolchain/distribution/install_distribution.sh

@@ -96,7 +96,7 @@ ensure_conda_env_python310() {
 
 if [ "$#" -ne 3 ]; then
   echo "Usage: $0 <environment_name> <distribution_name> <pip_dependencies>" >&2
-  echo "Example: $0 my_env local-inline 'numpy pandas scipy'" >&2
+  echo "Example: $0 my_env local-llama-8b 'numpy pandas scipy'" >&2
   exit 1
 fi
 

llama_toolchain/distribution/registry.py

@@ -28,7 +28,7 @@ def available_distribution_specs() -> List[DistributionSpec]:
     providers = api_providers()
     return [
         DistributionSpec(
-            spec_id="inline",
+            spec_id="local",
             description="Use code from `llama_toolchain` itself to serve all llama stack APIs",
             provider_specs={
                 Api.inference: providers[Api.inference]["meta-reference"],
@@ -42,8 +42,8 @@ def available_distribution_specs() -> List[DistributionSpec]:
             provider_specs={x: remote_spec(x) for x in providers},
         ),
         DistributionSpec(
-            spec_id="ollama-inline",
-            description="Like local-source, but use ollama for running LLM inference",
+            spec_id="local-ollama",
+            description="Like local, but use ollama for running LLM inference",
             provider_specs={
                 Api.inference: providers[Api.inference]["meta-ollama"],
                 Api.safety: providers[Api.safety]["meta-reference"],