huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: remove unused import and refactor test

Browse Source
This commit is contained in:
drbh 2024-10-31 19:25:35 -04:00
parent e2b394e3a0
commit d375e1e259
2 changed files with 4 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
integration-tests/models/test_flash_qwen2_vl.py
View File

@ -67,14 +67,10 @@ async def test_flash_qwen2_vl_simple_streaming(flash_qwen2, response_snapshot):
count = 0 count = 0
generated = "" generated = ""
last_response = None last_response = None
try: async for response in responses:
async for response in responses: count += 1
count += 1 generated += response.choices[0].delta.content
generated += response.choices[0].delta.content last_response = response
last_response = response
except Exception as e:
# handle when the client library raises an exception when it cant parse "[DONE]" as JSON
pass
assert ( assert (
generated generated

1
server/text_generation_server/models/custom_modeling/qwen2_vl.py
View File

@ -34,7 +34,6 @@ from text_generation_server.layers import (
TensorParallelColumnLinear, TensorParallelColumnLinear,
TensorParallelRowLinear, TensorParallelRowLinear,
TensorParallelEmbedding, TensorParallelEmbedding,
FastLinear,
SpeculativeHead, SpeculativeHead,
) )
from text_generation_server.layers.attention import ( from text_generation_server.layers.attention import (