s23deepak
/

streaming-vlm-qwen3-rocm

Model card Files Files and versions

streaming-vlm-qwen3-rocm

Ctrl+K

Ctrl+K

1 contributor

History: 31 commits

s23deepak's picture

Add ROCM_ACCELERATION.md — deep dive into ROCm model acceleration libraries and how they relate to StreamingVLM

f6c261b verified about 4 hours ago

scripts
Add DeepSpeed ZeRO-3 config about 5 hours ago
streaming_vlm
Add Qwen3-VL-2B support + CUDA flash_attention_2 config about 5 hours ago
.gitattributes

1.52 kB
initial commit about 5 hours ago
EXPLAINED.md

16 kB
Add EXPLAINED.md — deep dive into StreamingVLM architecture and patching methodology about 5 hours ago
MIGRATION_GUIDE.md

9.36 kB
Add MIGRATION_GUIDE.md about 5 hours ago
README.md

8.28 kB
Update ML Intern artifact metadata about 5 hours ago
ROCM_ACCELERATION.md

12.9 kB
Add ROCM_ACCELERATION.md — deep dive into ROCm model acceleration libraries and how they relate to StreamingVLM about 4 hours ago
requirements.txt

408 Bytes
Add requirements, setup, and training files about 5 hours ago
setup.py

843 Bytes
Add setup.py about 5 hours ago
test_imports.py

6.52 kB
Add test_imports.py about 5 hours ago
train.py

5.2 kB
Add train.py and test_imports.py about 5 hours ago