biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Remove mamba_ssm from vLLM requirements; install inside test container using --no-build-isolation (#22541)

Browse Source 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
Thomas Parnell
2025-08-09 08:05:32 +02:00
committed by GitHub
parent 23472ff51c
commit 8a0ffd6285
6 changed files with 26 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
requirements/test.in
View File

@@ -10,7 +10,7 @@ pytest-timeout
# testing utils
backoff # required for phi4mm test
blobfile # required for kimi-vl test
einops # required for MPT, qwen-vl and Mamba
einops # required for MPT, qwen-vl
httpx
librosa # required for audio tests
vector_quantize_pytorch # required for minicpmo_26 test
@@ -26,7 +26,6 @@ torch==2.7.1
torchaudio==2.7.1
torchvision==0.22.1
transformers_stream_generator # required for qwen-vl test
mamba_ssm==2.2.5 # required for plamo2 test
matplotlib # required for qwen-vl test
mistral_common[image,audio] >= 1.8.2 # required for voxtral test
num2words # required for smolvlm test
@@ -53,4 +52,4 @@ runai-model-streamer==0.11.0
runai-model-streamer-s3==0.11.0
fastsafetensors>=0.1.10
pydantic>=2.10 # 2.9 leads to error on python 3.10
terratorch==1.1rc2 # required for PrithviMAE test
terratorch==1.1rc2 # required for PrithviMAE test