Spaces:

Alovestocode
/

ZeroGPU-LLM-Inference

Running on Zero

App Files Files Community

ZeroGPU-LLM-Inference

165 kB

Ctrl+K

Ctrl+K

1 contributor

History: 83 commits

Alikestocode's picture

Add GPU estimator, DDG search, and cancel support

4ce42e8 11 months ago

.dockerignore

104 Bytes
Add Google Cloud Platform deployment configurations 11 months ago
.gitattributes

1.52 kB
Initial commit: ZeroGPU LLM Inference Space 11 months ago
.gitignore

27 Bytes
Add .gitignore and remove cache files 11 months ago
DEPLOYMENT_STATUS.md

2.21 kB
Add deployment status document after re-authentication 11 months ago
Dockerfile

1.02 kB
Fix delete_revisions import with fallback cache cleanup 11 months ago
FIX_PERMISSIONS.md

2.05 kB
Add permission fix guide for spherical-gate-477614-q7 project 11 months ago
LLM_COMPRESSOR_FEATURES.md

6.24 kB
Fix AWQModifier import path: use modifiers.awq instead of modifiers.quantization 11 months ago
MANUAL_DEPLOY.md

1.59 kB
Fix delete_revisions import with fallback cache cleanup 11 months ago
QUANTIZE_AWQ.md

3.21 kB
Fix AWQModifier import path: use modifiers.awq instead of modifiers.quantization 11 months ago
README.md

4.23 kB
Implement vLLM with LLM Compressor and performance optimizations 11 months ago
app.py

56.9 kB
Add GPU estimator, DDG search, and cancel support 11 months ago
apt.txt

11 Bytes
Initial commit: ZeroGPU LLM Inference Space 11 months ago
cloudbuild.yaml

1.36 kB
Add Cloud Build deployment script and permission setup helper 11 months ago
deploy-cloud-build.sh

3.31 kB
Add Cloud Build deployment script and permission setup helper 11 months ago
deploy-compute-engine.sh

4.23 kB
Add Google Cloud Platform deployment configurations 11 months ago
deploy-gcp.sh

2.67 kB
Add Google Cloud Platform deployment configurations 11 months ago
gcp-deployment.md

5.32 kB
Add Google Cloud Platform deployment configurations 11 months ago
quantize_to_awq_colab.ipynb

32.9 kB
Lower Gemma AWQ group size to 16 11 months ago
requirements.txt

397 Bytes
Clarify LLM Compressor optional status - vLLM has native AWQ support 11 months ago
setup-gcp-permissions.sh

1.8 kB
Add Cloud Build deployment script and permission setup helper 11 months ago
style.css

2.84 kB
Initial commit: ZeroGPU LLM Inference Space 11 months ago
test_api.py

3.43 kB
Migrate to AWQ quantization with FlashAttention-2 11 months ago
test_api_gradio_client.py

7.2 kB
Implement vLLM with LLM Compressor and performance optimizations 11 months ago
test_awq_models.py

3.12 kB
Add test scripts for AWQ models on ZeroGPU Space 11 months ago
test_quantization_notebook.py

9.84 kB
Update Qwen model to use AWQ quantized version 11 months ago
test_space_awq.sh

1.93 kB
Add test scripts for AWQ models on ZeroGPU Space 11 months ago
test_space_simple.py

3.49 kB
Add test scripts for AWQ models on ZeroGPU Space 11 months ago
test_space_simple.sh

1.68 kB
Fix delete_revisions import with fallback cache cleanup 11 months ago