A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 02:15 UTC
[Bugfix] Bump up mistral_common to support v13 tokenizer (#20905)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
22quinn committed
Jul 14, 2025 at 03:45 UTC
f326ab9c88c016607be0965743f73e6c4de610c0
2 files changed
+2
-2
requirements/test.in
+1
-1
@@ -28,7 +28,7 @@ torchvision==0.22.0
28
transformers_stream_generator # required for qwen-vl test
29
mamba_ssm # required for plamo2 test
30
matplotlib # required for qwen-vl test
31
-mistral_common[opencv] >= 1.6.2 # required for pixtral test
31
+mistral_common[opencv] >= 1.7.0 # required for pixtral test
32
num2words # required for smolvlm test
33
opencv-python-headless >= 4.11.0 # required for video test
34
datamodel_code_generator # required for minicpm3 test
requirements/test.txt
+1
-1
@@ -305,7 +305,7 @@ mbstrdecoder==1.1.3
305
# typepy
306
mdurl==0.1.2
307
# via markdown-it-py
308
-mistral-common==1.6.2
308
+mistral-common==1.7.0
309
# via -r requirements/test.in
310
more-itertools==10.5.0
311
# via lm-eval