tmp workflow

.github/workflows/publish-to-docker.yml

@@ -85,6 +85,15 @@ jobs:
         run: |
           docker images
 
+      - name: Start up built docker image
+        run: |
+          cd distributions/together
+          docker compose up
+
+      - name: Start up built docker image
+        run: |
+          llama-stack-client models list
+
       - name: Push to dockerhub
         run: |
           TEMPLATES=("ollama" "bedrock" "remote-vllm" "fireworks" "together" "tgi" "meta-reference-gpu")

distributions/fireworks/compose.yaml

@@ -1,13 +1,11 @@
 services:
   llamastack:
-    image: llamastack/distribution-fireworks
-    network_mode: "host"
-    volumes:
-      - ~/.llama:/root/.llama
-      - ./run.yaml:/root/llamastack-run-fireworks.yaml
+    image: llamastack/fireworks
     ports:
       - "8321:8321"
-    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-fireworks.yaml"
+    environment:
+      - FIREWORKS_API_KEY=${FIREWORKS_API_KEY}
+    entrypoint: bash -c "llama stack run fireworks"
     deploy:
       restart_policy:
         condition: on-failure

distributions/together/compose.yaml

@@ -1,13 +1,11 @@
 services:
   llamastack:
-    image: llamastack/distribution-together
-    network_mode: "host"
-    volumes:
-      - ~/.llama:/root/.llama
-      - ./run.yaml:/root/llamastack-run-together.yaml
+    image: llamastack/together
     ports:
       - "8321:8321"
-    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-together.yaml"
+    environment:
+      - TOGETHER_API_KEY=${TOGETHER_API_KEY}
+    entrypoint: bash -c "llama stack run together"
     deploy:
       restart_policy:
         condition: on-failure

llama_stack/cli/stack/run.py

@@ -6,6 +6,7 @@
 
 import argparse
 import os
+import sys
 from pathlib import Path
 
 from llama_stack.cli.subcommand import Subcommand
@@ -70,7 +71,7 @@ class StackRun(Subcommand):
             BUILDS_BASE_DIR,
             DISTRIBS_BASE_DIR,
         )
-        from llama_stack.distribution.utils.exec import run_with_pty
+        from llama_stack.distribution.utils.exec import run_command, run_with_pty
 
         if not args.config:
             self.parser.error("Must specify a config file to run")
@@ -190,4 +191,8 @@ class StackRun(Subcommand):
                 return
             run_args.extend(["--env", f"{key}={value}"])
 
-        run_with_pty(run_args)
+        is_terminal = os.isatty(sys.stdout.fileno())
+        if is_terminal:
+            run_with_pty(run_args)
+        else:
+            run_command(run_args)