Spaces:

encryptd
/

ocr_vlm_nuextract3

Paused

App Files Files Community

ocr_vlm_nuextract3

Commit History

Jun 1

04:50
Optimize speculative decoding performance by increasing max_num_batched_tokens to 4096

encryptd

a0613f9
04:41
Fix entrypoint override in Dockerfile

encryptd

8c76968
04:37
Fix HF space build error by using official vllm-openai:v0.21.0 base image

encryptd

0a0b8ea
04:11
Remove torchvision pin to allow vllm 0.12.0 to resolve its own torchvision dependency

encryptd

a35ce3f
04:03
Upgrade to vllm 0.12.0 and restore original performance arguments for Qwen 3.5 support

encryptd

1cc1c9e
03:53
Pin transformers to 4.48.2 to satisfy vllm>=4.48.2 dependency and resolve TokenizersBackend AttributeError

encryptd

ee926f5
03:50
Pin transformers to 4.48.0 to resolve TokenizersBackend AttributeError in vLLM 0.8.0

encryptd

ab83d82
03:45
Remove limit-mm-per-prompt argument to bypass vLLM 0.8.0 multimodal registration check

encryptd

c2fa736
03:41
Remove speculative-config argument for vLLM 0.8.0 CLI parser

encryptd

20df6b8
03:36
Fix limit-mm-per-prompt syntax for vLLM 0.8.0 CLI parser

encryptd

7f9201a
03:30
Update torch to 2.6.0+cu124 and torchvision to 0.21.0+cu124 to satisfy vllm 0.8.0 dependency requirements

encryptd

860dc84
03:27
Downgrade torch to 2.5.1+cu124 and vllm to 0.8.0 to match available CUDA 12.4 pre-compiled wheels

encryptd

bdb058c
03:25
Fix NVIDIA driver mismatch on HF Space by forcing +cu124 torch wheels

encryptd

ba7160f
02:05
Fix: Upgrade to vLLM 0.22.0 and PyTorch 2.11.0 on CUDA 12.4 for native Qwen 3.5 support and host compatibility

encryptd

359492c
01:58
Fix: Remove speculative-config argument for vLLM 0.7.2 CLI compliance

encryptd

e776eb6
01:53
Fix: Update --limit-mm-per-prompt format to KEY=VALUE format image=99 for vLLM 0.7.2

encryptd

a5a317d
01:47
Fix: Align vLLM arguments with model card recommendations (chat format, MTP speculative config, limit-mm-per-prompt)

encryptd

244de46
01:37
Fix: Change wheel index to cu124 and pin torch to 2.5.1+cu124 for native CUDA 12.4 host driver compatibility

encryptd

c6032e7
01:30
Fix: Remove manual transformers source install to resolve tokenizer AttributeError

encryptd

4222b36
01:21
Fix: Remove limit-mm-per-prompt and mm-processor-kwargs for vLLM 0.7.2 compatibility

encryptd

9700b91

May 31

17:48
Fix: Update --limit-mm-per-prompt format to KEY=VALUE for vLLM 0.7.2 compatibility

encryptd

b7c3dd4
17:40
Fix: Pin torch to 2.5.1+cu121 and vllm to 0.7.2 to guarantee CUDA 12.4 host driver compatibility

encryptd

d1fc8a9
17:37
Fix: Add LD_LIBRARY_PATH forward compatibility for older host GPU drivers

encryptd

d16bf2a
17:26
Fix: Switch base to CUDA devel image to provide nvcc for flashinfer JIT, and add .gitignore

encryptd

2ea1c55
07:55
Fix: Remove show_copy_button parameter from gr.Textbox for Gradio 6 compatibility

encryptd

5aa37ab

May 30

19:04
Fix: Remove audioop-lts as Python 3.10 natively provides audioop

encryptd

eeebc77
19:01
Migration: Convert Hugging Face Space to custom Docker Space using CUDA 12.4

encryptd

f1ba762
18:58
Fix: Install transformers from source to support Qwen 3.5 architecture

encryptd

7eb1ffe
18:49
Initial commit: NuExtract3 Gradio space setup powered by vLLM on A100 GPU

encryptd

88dbb61

Commit History

Jun 1

Optimize speculative decoding performance by increasing max_num_batched_tokens to 4096

Fix entrypoint override in Dockerfile

Fix HF space build error by using official vllm-openai:v0.21.0 base image

Remove torchvision pin to allow vllm 0.12.0 to resolve its own torchvision dependency

Upgrade to vllm 0.12.0 and restore original performance arguments for Qwen 3.5 support

Pin transformers to 4.48.2 to satisfy vllm>=4.48.2 dependency and resolve TokenizersBackend AttributeError

Pin transformers to 4.48.0 to resolve TokenizersBackend AttributeError in vLLM 0.8.0

Remove limit-mm-per-prompt argument to bypass vLLM 0.8.0 multimodal registration check

Remove speculative-config argument for vLLM 0.8.0 CLI parser

Fix limit-mm-per-prompt syntax for vLLM 0.8.0 CLI parser

Update torch to 2.6.0+cu124 and torchvision to 0.21.0+cu124 to satisfy vllm 0.8.0 dependency requirements

Downgrade torch to 2.5.1+cu124 and vllm to 0.8.0 to match available CUDA 12.4 pre-compiled wheels

Fix NVIDIA driver mismatch on HF Space by forcing +cu124 torch wheels

Fix: Upgrade to vLLM 0.22.0 and PyTorch 2.11.0 on CUDA 12.4 for native Qwen 3.5 support and host compatibility

Fix: Remove speculative-config argument for vLLM 0.7.2 CLI compliance

Fix: Update --limit-mm-per-prompt format to KEY=VALUE format image=99 for vLLM 0.7.2

Fix: Align vLLM arguments with model card recommendations (chat format, MTP speculative config, limit-mm-per-prompt)

Fix: Change wheel index to cu124 and pin torch to 2.5.1+cu124 for native CUDA 12.4 host driver compatibility

Fix: Remove manual transformers source install to resolve tokenizer AttributeError

Fix: Remove limit-mm-per-prompt and mm-processor-kwargs for vLLM 0.7.2 compatibility

May 31

Fix: Update --limit-mm-per-prompt format to KEY=VALUE for vLLM 0.7.2 compatibility

Fix: Pin torch to 2.5.1+cu121 and vllm to 0.7.2 to guarantee CUDA 12.4 host driver compatibility

Fix: Add LD_LIBRARY_PATH forward compatibility for older host GPU drivers

Fix: Switch base to CUDA devel image to provide nvcc for flashinfer JIT, and add .gitignore

Fix: Remove show_copy_button parameter from gr.Textbox for Gradio 6 compatibility

May 30

Fix: Remove audioop-lts as Python 3.10 natively provides audioop

Migration: Convert Hugging Face Space to custom Docker Space using CUDA 12.4

Fix: Install transformers from source to support Qwen 3.5 architecture

Initial commit: NuExtract3 Gradio space setup powered by vLLM on A100 GPU