You can deploy this model and start earning money today!

AXERA-TECH/
PaddleOCR-VL-1.5

Name: PaddleOCR-VL-1.5
Availability: InStock

PaddlePaddle/PaddleOCR-VL-1.5

finetune

bsd-3-clause

endpoints_compatible

Views

No views yet

PaddleOCR-VL-1.5

This version of PaddleOCR-VL-1.5 has been converted to run on the Axera NPU using w4a16 quantization.

Compatible with Pulsar2 version: 5.0

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through the original repo:

Support Platform

AX650
- AX650N DEMO Board
- M4N-Dock(爱芯派Pro)
- M.2 Accelerator card

Image Process

Chips	input size	image num	ViT encoder	TTFT (640 tokens)	Decode speed	CMM	Flash
AX650	576x768	1	1685.554 ms	361.8 ms	44.6 tokens/sec	TBD	TBD

How to use

安装 axllm

方式一：克隆仓库后执行安装脚本：

shell

git clone -b axllm https://github.com/AXERA-TECH/ax-llm.git
cd ax-llm
./install.sh

方式二：一行命令安装 (默认分支 axllm)：

curl -fsSL https://raw.githubusercontent.com/AXERA-TECH/ax-llm/axllm/install.sh | bash

方式三：下载 Github Actions CI 导出的可执行程序 (适合没有编译环境的用户)：

如果没有编译环境, 请到： https://github.com/AXERA-TECH/ax-llm/actions?query=branch%3Aaxllm 下载 最新 CI 导出的可执行程序 (axllm), 然后：

shell

chmod +x axllm
sudo mv axllm /usr/bin/axllm

本仓库也包含一个已经验证过的 AX650/AX650N aarch64 axllm 二进制，可直接在本仓库目录下运行：

shell

chmod +x ./bin/axllm
./bin/axllm serve . --port 8000

该二进制的来源和校验信息记录在 bin/axllm.version.json 中。

模型下载 (Hugging Face)

先创建模型目录并进入, 然后下载到该目录：

shell

mkdir -p AXERA-TECH/PaddleOCR-VL-1.5
cd AXERA-TECH/PaddleOCR-VL-1.5
hf download AXERA-TECH/PaddleOCR-VL-1.5 --local-dir .

# 下载后目录结构
tree -L 1
.
|-- README.md
|-- assets
|-- config.json
|-- model.embed_tokens.weight.bfloat16.bin
|-- paddleocr_vl_p128_l0_together.axmodel
...
|-- paddleocr_vl_p128_l17_together.axmodel
|-- paddleocr_vl_post.axmodel
|-- post_config.json
|-- python
|-- tokenizer.model
|-- vision_cache
`-- vit_576x768.axmodel

Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) or AX650N DEMO Board

运行 (CLI)

axllm run AXERA-TECH/PaddleOCR-VL-1.5/

启动后进入交互模式.每轮输入 prompt 后, 会提示 image >>：

直接回车：仅文本对话
输入图片路径：图文 OCR 对话

输入图像示例:

shell

root@ax650 # axllm run AXERA-TECH/PaddleOCR-VL-1.5/ # 注意使用最新版本的 axllm
45:21.515 INF Init:218 | LLM init start
tokenizer_type = 0
 95% | ##############################   |  20 /  21 [1.97s<2.07s, 10.13 count/s] init post axmodel ok,remain_cmm(4330 MB)
45:23.490 INF Init:368 | max_token_len : 2047
45:23.490 INF Init:371 | kv_cache_size : 256, kv_cache_num: 2047
45:23.490 INF Init:374 | prefill_token_num : 128
45:23.490 INF Init:379 | grp: 1, prefill_max_kv_cache_num : 1
45:23.490 INF Init:379 | grp: 2, prefill_max_kv_cache_num : 128
45:23.490 INF Init:379 | grp: 3, prefill_max_kv_cache_num : 256
45:23.490 INF Init:379 | grp: 4, prefill_max_kv_cache_num : 384
45:23.490 INF Init:379 | grp: 5, prefill_max_kv_cache_num : 512
45:23.490 INF Init:379 | grp: 6, prefill_max_kv_cache_num : 640
45:23.490 INF Init:384 | prefill_max_token_num : 640
45:23.490 INF Init:27 | LLaMaEmbedSelector use mmap
100% | ################################ |  21 /  21 [1.98s<1.98s, 10.62 count/s] embed_selector init ok
45:24.028 INF Init:453 | PaddleOCRVL: encoder input nSize=5334336 -> eff_nSize=1333584 (float32 input)
45:24.029 WRN Init:469 | Qwen-VL vision size override: cfg=448x448 bytes=602112, model_input_bytes=5334336 -> 756x588 (factor-search).
45:24.029 INF Init:661 | PaddleOCR-VL token ids: vision_start=101305 image_pad=100295 video_pad=100295
45:24.029 INF Init:686 | VisionModule init ok: type=PaddleOCRVL, tokens_per_block=567, embed_size=1024, out_dtype=fp32
45:24.029 WRN Init:695 | Vision preprocess backend: SimpleCV (OpenCV not found at build time; minor differences vs OpenCV are possible)
45:24.031 INF load_config:282 | load config:
45:24.031 INF load_config:282 | {
45:24.031 INF load_config:282 |     "enable_repetition_penalty": false,
45:24.031 INF load_config:282 |     "enable_temperature": false,
45:24.031 INF load_config:282 |     "enable_top_k_sampling": false,
45:24.031 INF load_config:282 |     "enable_top_p_sampling": false,
45:24.031 INF load_config:282 |     "penalty_window": 20,
45:24.031 INF load_config:282 |     "repetition_penalty": 1.0,
45:24.031 INF load_config:282 |     "temperature": 0.6,
45:24.031 INF load_config:282 |     "top_k": 1,
45:24.031 INF load_config:282 |     "top_p": 0.9
45:24.031 INF load_config:282 | }
45:24.031 INF Init:448 | LLM init ok
Commands:
  /q, /exit  退出
  /reset     重置 kvcache
  /dd        删除一轮对话
  /pp        打印历史对话
Ctrl+C: 停止当前生成
VLM enabled: after each prompt, input image path (empty = text-only). Use "video:<frames_dir>" for video.
----------------------------------------
prompt >> OCR:
image >> /Path/To/Your/AXERA-TECH/PaddleOCR-VL-1.5/assets/IMG_0462.JPG
45:30.031 INF EncodeForContent:1058 | PaddleOCRVL pixel_values bytes=1333584 min=0 max=255 (w=756 h=588 ps=14)
45:31.726 INF EncodeForContent:1102 | vision cache store: /Path/To/Your/AXERA-TECH/PaddleOCR-VL-1.5/assets/IMG_0462.JPG
45:31.760 INF SetKVCache:747 | prefill_grpid:6 kv_cache_num:640 precompute_len:0 input_num_token:596
45:31.760 INF SetKVCache:749 | current prefill_max_token_num:640
45:31.760 INF SetKVCache:752 | first run
45:31.761 INF Run:805 | input token num : 596, prefill_split_num : 5
45:31.761 INF Run:845 | prefill chunk p=0 history_len=0 grpid=1 kv_cache_num=0 input_tokens=128
45:31.761 INF Run:868 | prefill indices shape: p=0 idx_elems=384 idx_rows=3 pos_rows=3
45:31.815 INF Run:845 | prefill chunk p=1 history_len=128 grpid=2 kv_cache_num=128 input_tokens=128
45:31.816 INF Run:868 | prefill indices shape: p=1 idx_elems=384 idx_rows=3 pos_rows=3
45:31.873 INF Run:845 | prefill chunk p=2 history_len=256 grpid=3 kv_cache_num=256 input_tokens=128
45:31.873 INF Run:868 | prefill indices shape: p=2 idx_elems=384 idx_rows=3 pos_rows=3
45:31.937 INF Run:845 | prefill chunk p=3 history_len=384 grpid=4 kv_cache_num=384 input_tokens=128
45:31.937 INF Run:868 | prefill indices shape: p=3 idx_elems=384 idx_rows=3 pos_rows=3
45:32.006 INF Run:845 | prefill chunk p=4 history_len=512 grpid=5 kv_cache_num=512 input_tokens=84
45:32.006 INF Run:868 | prefill indices shape: p=4 idx_elems=384 idx_rows=3 pos_rows=3
45:32.088 INF Run:1010 | ttft: 327.20 ms
James Landay-VR
14175

45:32.374 NTC Run:1132 | hit eos,avg 38.47 token/s
45:32.374 INF GetKVCache:721 | precompute_len:597, remaining:43

启动服务(OpenAI 兼容)

axllm serve AXERA-TECH/PaddleOCR-VL-1.5/

参考日志如下:

shell

root@ax650 # axllm serve AXERA-TECH/PaddleOCR-VL-1.5/ # 注意使用最新版本的 axllm
20:47:54.027 INF Init:218 | LLM init start
tokenizer_type = 0
 95% | ##############################   |  20 /  21 [1.96s<2.05s, 10.22 count/s] init post axmodel ok,remain_cmm(4330 MB)
20:47:55.983 INF Init:368 | max_token_len : 2047
20:47:55.983 INF Init:371 | kv_cache_size : 256, kv_cache_num: 2047
20:47:55.983 INF Init:374 | prefill_token_num : 128
20:47:55.983 INF Init:379 | grp: 1, prefill_max_kv_cache_num : 1
20:47:55.983 INF Init:379 | grp: 2, prefill_max_kv_cache_num : 128
20:47:55.983 INF Init:379 | grp: 3, prefill_max_kv_cache_num : 256
20:47:55.983 INF Init:379 | grp: 4, prefill_max_kv_cache_num : 384
20:47:55.983 INF Init:379 | grp: 5, prefill_max_kv_cache_num : 512
20:47:55.983 INF Init:379 | grp: 6, prefill_max_kv_cache_num : 640
20:47:55.983 INF Init:384 | prefill_max_token_num : 640
20:47:55.983 INF Init:27 | LLaMaEmbedSelector use mmap
100% | ################################ |  21 /  21 [1.96s<1.96s, 10.72 count/s] embed_selector init ok
20:47:56.526 INF Init:453 | PaddleOCRVL: encoder input nSize=5334336 -> eff_nSize=1333584 (float32 input)
20:47:56.526 WRN Init:469 | Qwen-VL vision size override: cfg=448x448 bytes=602112, model_input_bytes=5334336 -> 756x588 (factor-search).
20:47:56.526 INF Init:661 | PaddleOCR-VL token ids: vision_start=101305 image_pad=100295 video_pad=100295
20:47:56.526 INF Init:686 | VisionModule init ok: type=PaddleOCRVL, tokens_per_block=567, embed_size=1024, out_dtype=fp32
20:47:56.526 WRN Init:695 | Vision preprocess backend: SimpleCV (OpenCV not found at build time; minor differences vs OpenCV are possible)
20:47:56.528 INF load_config:282 | load config:
20:47:56.528 INF load_config:282 | {
20:47:56.528 INF load_config:282 |     "enable_repetition_penalty": false,
20:47:56.528 INF load_config:282 |     "enable_temperature": false,
20:47:56.528 INF load_config:282 |     "enable_top_k_sampling": false,
20:47:56.528 INF load_config:282 |     "enable_top_p_sampling": false,
20:47:56.528 INF load_config:282 |     "penalty_window": 20,
20:47:56.528 INF load_config:282 |     "repetition_penalty": 1.0,
20:47:56.528 INF load_config:282 |     "temperature": 0.6,
20:47:56.528 INF load_config:282 |     "top_k": 1,
20:47:56.528 INF load_config:282 |     "top_p": 0.9
20:47:56.528 INF load_config:282 | }
20:47:56.528 INF Init:448 | LLM init ok
Starting server on port 8000 with model 'AXERA-TECH/PaddleOCR-VL-1.5'...
API URLs:
  GET  http://127.0.0.1:8000/health
  GET  http://127.0.0.1:8000/v1/models
  POST http://127.0.0.1:8000/v1/chat/completions
  GET  http://10.168.232.217:8000/health
  GET  http://10.168.232.217:8000/v1/models
  POST http://10.168.232.217:8000/v1/chat/completions
  GET  http://172.17.0.1:8000/health
  GET  http://172.17.0.1:8000/v1/models
  POST http://172.17.0.1:8000/v1/chat/completions
Aliases:
  GET  http://127.0.0.1:8000/models
  POST http://127.0.0.1:8000/chat/completions
  GET  http://10.168.232.217:8000/models
  POST http://10.168.232.217:8000/chat/completions
  GET  http://172.17.0.1:8000/models
  POST http://172.17.0.1:8000/chat/completions
OpenAI API Server starting on http://0.0.0.0:8000
Max concurrency: 1
Models: AXERA-TECH/PaddleOCR-VL-1.5

Python Inference (可选)

Python 推理脚本保留在 python/ 目录下, 可在 PC/开发板上使用 Python 进行推理测试.

shell

python3 python/infer_axmodel.py \
  --hf_model ./python/paddleocr_vl_1-5_tokenizer \
  --axmodel_path . \
  --vit_model_path ./vit_576x768.axmodel \
  --image_path ./assets/IMG_0462.JPG \
  --task ocr

支持的任务类型 (--task)：

ocr — 通用文字识别
table — 表格识别
chart — 图表识别
formula — 公式识别
spotting — 文字检测(Spotting)
seal — 印章识别

End-to-End Metrics (AX650N)

Metric	Value
Max TTFT (640 tokens)	361.8 ms
Decode speed	44.6 tokens/s
ViT latency (576x768)	1685.554 ms

Subgraph Latency

Stage	Subgraph	Latency
Prefill	g1	2.551 ms
Prefill	g2	2.883 ms
Prefill	g3	3.158 ms
Prefill	g4	3.413 ms
Prefill	g5	3.795 ms
Prefill	g6	4.007 ms
Decode	g0	0.949 ms
Post-process	-	5.313 ms
ViT	-	1685.554 ms

Discussion

GitHub Issues
QQ Group: 139953715