mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-01-27 08:49:32 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: Yi models (#651)

Browse Source 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-11-14 21:55:24 -05:00
committed by GitHub
parent b4b70e2f20
commit 6a6d689a77
8 changed files with 115 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
openllm-python/src/openllm_cli/entrypoint.py
View File

@@ -277,7 +277,7 @@ class OpenLLMCommandGroup(BentoMLCommandGroup):
def list_commands(self, ctx: click.Context) -> list[str]:
return super().list_commands(ctx) + t.cast('Extensions', extension_command).list_commands(ctx)
def command(self, *args: t.Any, **kwargs: t.Any) -> t.Callable[[t.Callable[..., t.Any]], click.Command]: # type: ignore[override] # XXX: fix decorator on BentoMLCommandGroup
def command(self, *args: t.Any, **kwargs: t.Any) -> t.Callable[[t.Callable[..., t.Any]], click.Command]:
"""Override the default 'cli.command' with supports for aliases for given command, and it wraps the implementation with common parameters."""
if 'context_settings' not in kwargs:
kwargs['context_settings'] = {}
@@ -457,7 +457,6 @@ def start_command(
quantize=quantize,
serialisation=serialisation,
torch_dtype=dtype,
trust_remote_code=check_bool_env('TRUST_REMOTE_CODE'),
)
backend_warning(llm.__llm_backend__)
@@ -635,6 +634,7 @@ def process_environ(
'OPENLLM_BACKEND': llm.__llm_backend__,
'OPENLLM_CONFIG': config.model_dump_json(flatten=True).decode(),
'TORCH_DTYPE': str(llm._torch_dtype).split('.')[-1],
'TRUST_REMOTE_CODE': str(llm.trust_remote_code),
}
)
if llm.quantise: