container: update tracing dependencies (#591)

* chore: update build message Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com> * chore: add tracing dependencies to container Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com> --------- Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
bentoml · Nov 8, 2023 · e87830e · e87830e
1 parent 0ea025d
commit e87830e
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 4 deletions.
diff --git a/openllm-python/src/openllm/bundle/_package.py b/openllm-python/src/openllm/bundle/_package.py
@@ -63,7 +63,7 @@ def build_editable(path: str, package: t.Literal['openllm', 'openllm_core', 'ope
       return builder.build('wheel', path, config_settings={'--global-option': '--quiet'})
   raise RuntimeError('Custom OpenLLM build is currently not supported. Please install OpenLLM from PyPI or built it from Git source.')
 
-def construct_python_options(llm: openllm.LLM[t.Any, t.Any], llm_fs: FS, extra_dependencies: tuple[str, ...] | None = None, adapter_map: dict[str, str] | None = None,) -> PythonOptions:
+def construct_python_options(llm: openllm.LLM[t.Any, t.Any], llm_fs: FS, extra_dependencies: tuple[str, ...] | None = None, adapter_map: dict[str, str] | None = None) -> PythonOptions:
   packages = ['openllm', 'scipy']  # apparently bnb misses this one
   if adapter_map is not None: packages += ['openllm[fine-tune]']
   # NOTE: add openllm to the default dependencies
@@ -81,7 +81,7 @@ def construct_python_options(llm: openllm.LLM[t.Any, t.Any], llm_fs: FS, extra_d
   env['backend_value']
   if not openllm_core.utils.is_torch_available():
     raise ValueError('PyTorch is not available. Make sure to have it locally installed.')
-  packages.extend(['torch==2.0.1+cu118', 'vllm==0.2.1.post1', 'xformers==0.0.22'])  # XXX: Currently locking this for correctness
+  packages.extend(['torch==2.0.1+cu118', 'vllm==0.2.1.post1', 'xformers==0.0.22', 'bentoml[tracing]==1.1.9'])  # XXX: Currently locking this for correctness
   wheels: list[str] = []
   built_wheels = [build_editable(llm_fs.getsyspath('/'), t.cast(t.Literal['openllm', 'openllm_core', 'openllm_client'], p)) for p in ('openllm_core', 'openllm_client', 'openllm')]
   if all(i for i in built_wheels):

diff --git a/openllm-python/src/openllm/cli/_factory.py b/openllm-python/src/openllm/cli/_factory.py
@@ -200,6 +200,8 @@ def start_cmd(ctx: click.Context, /, server_timeout: int, model_id: str | None,
     def next_step(model_name: str, adapter_map: DictStrAny | None) -> None:
       cmd_name = f'openllm build {model_name}'
       if not llm._local: cmd_name += f' --model-id {llm.model_id}'
+      if llm._quantise: cmd_name += f' --quantize {llm._quantise}'
+      cmd_name += f' --serialization {_serialisation}'
       if adapter_map is not None:
         cmd_name += ' ' + ' '.join([f'--adapter-id {s}' for s in [f'{p}:{name}' if name not in (None, 'default') else p for p, name in adapter_map.items()]])
       if not openllm.utils.get_quiet_mode():
@@ -212,10 +214,9 @@ def next_step(model_name: str, adapter_map: DictStrAny | None) -> None:
     else:
       try:
         server.start(env=start_env, text=True, blocking=True)
-      except KeyboardInterrupt:
-        next_step(model, adapter_map)
       except Exception as err:
         termui.echo(f'Error caught while running LLM Server:\n{err}', fg='red')
+        raise
       else:
         next_step(model, adapter_map)