mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-03-05 07:36:15 -05:00
Code Issues Packages Projects Releases Wiki Activity

refactor: use DEBUG env-var instead of OPENLLMDEVDEBUG (#647)

Browse Source 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-11-14 01:39:58 -05:00
committed by GitHub
parent d63da6a5cb
commit 31a799ff61
7 changed files with 6 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
openllm-python/src/openllm/bundle/oci/__init__.py
View File

@@ -213,7 +213,7 @@ def build_container(
tags['image_sha'] = outputs.decode('utf-8').strip()
except Exception as err:
raise openllm.exceptions.OpenLLMException(
f'Failed to containerize base container images (Scroll up to see error above, or set OPENLLMDEVDEBUG=True for more traceback):\n{err}'
f'Failed to containerize base container images (Scroll up to see error above, or set DEBUG=5 for more traceback):\n{err}'
) from err
return tags

4
openllm-python/src/openllm/entrypoints/cohere.py
View File

@@ -147,8 +147,8 @@ async def cohere_generate(req: Request, llm: openllm.LLM[M, T]) -> Response:
return StreamingResponse(generate_stream_generator(), media_type='text/event-stream')
# None-streaming case
final_result: GenerationOutput | None = None
texts: list[list[str]] = [[]] * config['num_generations']
token_ids: list[list[int]] = [[]] * config['num_generations']
texts: list[list[str]] = [[]] * config['n']
token_ids: list[list[int]] = [[]] * config['n']
async for res in result_generator:
if await req.is_disconnected():
return error_response(HTTPStatus.BAD_REQUEST, 'Client disconnected.')

1
openllm-python/src/openllm/playground/falcon_tuned.py
View File

@@ -8,7 +8,6 @@ import typing as t
import torch
import transformers
# import openllm here for OPENLLMDEVDEBUG
import openllm
# Make sure to have at least one GPU to run this script

1
openllm-python/src/openllm/playground/llama2_qlora.py
View File

@@ -8,7 +8,6 @@ import typing as t
import torch
import transformers
# import openllm here for OPENLLMDEVDEBUG
import openllm
if t.TYPE_CHECKING:

1
openllm-python/src/openllm/playground/opt_tuned.py
View File

@@ -7,7 +7,6 @@ import typing as t
import transformers
# import openllm here for OPENLLMDEVDEBUG
import openllm
# Make sure to have at least one GPU to run this script