Spaces:

encryptd
/

ocr_vlm_nuextract3

Sleeping

App Files Files Community

ocr_vlm_nuextract3

18.8 kB

Ctrl+K

Ctrl+K

1 contributor

History: 29 commits

encryptd

Optimize speculative decoding performance by increasing max_num_batched_tokens to 4096

a0613f9 1 day ago

.agent
Initial commit: NuExtract3 Gradio space setup powered by vLLM on A100 GPU 2 days ago
.agents
Initial commit: NuExtract3 Gradio space setup powered by vLLM on A100 GPU 2 days ago
.gitignore

64 Bytes
Fix: Switch base to CUDA devel image to provide nvcc for flashinfer JIT, and add .gitignore 1 day ago
Dockerfile

689 Bytes
Fix entrypoint override in Dockerfile 1 day ago
README.md

348 Bytes
Migration: Convert Hugging Face Space to custom Docker Space using CUDA 12.4 2 days ago
app.py

5.8 kB
Optimize speculative decoding performance by increasing max_num_batched_tokens to 4096 1 day ago
handover.md

5.15 kB
Remove torchvision pin to allow vllm 0.12.0 to resolve its own torchvision dependency 1 day ago
requirements.txt

36 Bytes
Fix HF space build error by using official vllm-openai:v0.21.0 base image 1 day ago