Fu DaiandClaude Opus 4.8
1a585693be
FastAPI service wrapping the Surya-OCR-2 model (datalab-to) served through vLLM: legacy /v1/api/ai/* endpoints, an OpenAI-compatible /v1/chat/completions endpoint, a coalescing request batcher, a local OCR CLI, Docker packaging, multilingual example outputs, and quantization/concurrency benchmarks. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
67 lines
2.0 KiB
Docker
67 lines
2.0 KiB
Docker
FROM vllm/vllm-openai:v0.20.1
|
|
|
|
ARG DEBIAN_FRONTEND=noninteractive
|
|
|
|
RUN apt-get update && \
|
|
apt-get install --no-install-recommends -y \
|
|
ffmpeg \
|
|
libsm6 \
|
|
libxext6 \
|
|
libcairo2 \
|
|
libgirepository1.0-dev \
|
|
libdbus-1-3 \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
ENV PYTHONUNBUFFERED=1
|
|
ENV PYTHONPATH=/opt/suya-ocr
|
|
|
|
ENV SURYA_MODEL_CHECKPOINT=datalab-to/surya-ocr-2
|
|
ENV SURYA_INFERENCE_BACKEND=vllm
|
|
ENV SURYA_INFERENCE_URL=http://127.0.0.1:8000/v1
|
|
ENV SURYA_INFERENCE_AUTOSTART=false
|
|
ENV SURYA_INFERENCE_KEEP_ALIVE=false
|
|
ENV SURYA_INFERENCE_PARALLEL=8
|
|
ENV SURYA_INFERENCE_LOGPROBS=false
|
|
ENV SURYA_INFERENCE_MAX_RETRIES=1
|
|
# Cap concurrent in-flight chat-completion requests to vLLM per coalesced batch.
|
|
# Must track VLLM_MAX_NUM_SEQS below: the request batcher otherwise ran only
|
|
# SURYA_INFERENCE_PARALLEL(=8) wide, leaving half of vLLM's 16 sequence slots
|
|
# idle. Setting this to 16 closed a 33% mean / 32% p95 regression (see
|
|
# docs/diagnosis_baseline.md). Do not exceed VLLM_MAX_NUM_SEQS (overcommit only
|
|
# queues).
|
|
ENV SURYA_INFERENCE_MAX_INFLIGHT=16
|
|
|
|
ENV SUYA_OCR_MODE=block
|
|
ENV SUYA_MAX_BATCH_SIZE=8
|
|
ENV SUYA_BATCH_WAIT_MS=25
|
|
ENV SUYA_MAX_QUEUE_SIZE=128
|
|
ENV SUYA_VLLM_IMAGE_FORMAT=JPEG
|
|
ENV SUYA_VLLM_JPEG_QUALITY=92
|
|
ENV SURYA_MAX_BLOCKS_PER_PAGE=80
|
|
ENV SURYA_MAX_TOKENS_FULL_PAGE=6144
|
|
|
|
# GPU/dtype defaults target T4 (deployment hardware). Do not change these
|
|
# without confirming the deployment target.
|
|
ENV VLLM_GPU_TYPE=t4
|
|
ENV VLLM_DTYPE=float16
|
|
ENV VLLM_GPU_MEMORY_UTILIZATION=0.85
|
|
ENV VLLM_MAX_MODEL_LEN=18000
|
|
ENV VLLM_MAX_NUM_SEQS=16
|
|
ENV VLLM_MAX_BATCHED_TOKENS=4096
|
|
# Latency-tuned vLLM serve flags (CUDA graph, prefix caching, chunked prefill)
|
|
# are applied in scripts/start_single_container.sh — see that file and
|
|
# docs/quantization_benchmark_results.md §5 for the measured rationale.
|
|
|
|
WORKDIR /opt/suya-ocr
|
|
|
|
COPY requirements.txt pyproject.toml ./
|
|
RUN pip install --no-cache-dir uv==0.8.15 && \
|
|
python3 -m uv pip install --system -r requirements.txt
|
|
|
|
COPY . .
|
|
|
|
EXPOSE 5002
|
|
|
|
ENTRYPOINT []
|
|
CMD ["/opt/suya-ocr/scripts/start_single_container.sh"]
|