Merge pull request #276 from makaveli10/fix_tensorrt_docker_deps

Upgrade tensorrt-llm==`0.10.0`.

README.md

@@ -127,10 +127,10 @@ client(hls_url="http://as-hls-ww-live.akamaized.net/pool_904/live/ww/bbc_1xtra/b
   ```bash
   docker run -p 9090:9090 --runtime=nvidia --gpus all --entrypoint /bin/bash -it ghcr.io/collabora/whisperlive-tensorrt
 
-  # Build tiny.en engine
+  # Build small.en engine
   bash build_whisper_tensorrt.sh /app/TensorRT-LLM-examples small.en
 
-  # Run server with tiny.en
+  # Run server with small.en
   python3 run_server.py --port 9090 \
                         --backend tensorrt \
                         --trt_model_path "/app/TensorRT-LLM-examples/whisper/whisper_small_en"

docker/Dockerfile.tensorrt

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04
+FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04 AS base
 
 ARG DEBIAN_FRONTEND=noninteractive
 
@@ -6,14 +6,16 @@ RUN apt-get update && apt-get install -y \
     python3.10 python3-pip openmpi-bin libopenmpi-dev git wget \
     && rm -rf /var/lib/apt/lists/*
 
-RUN pip3 install --no-cache-dir -U tensorrt_llm==0.9.0 --extra-index-url https://pypi.nvidia.com
-
+FROM base AS devel
+RUN pip3 install --no-cache-dir -U tensorrt_llm==0.10.0 --extra-index-url https://pypi.nvidia.com
 WORKDIR /app
-
-RUN git clone -b v0.9.0 --depth 1 https://github.com/NVIDIA/TensorRT-LLM.git && \
+RUN git clone -b v0.10.0 --depth 1 https://github.com/NVIDIA/TensorRT-LLM.git && \
     mv TensorRT-LLM/examples ./TensorRT-LLM-examples && \
     rm -rf TensorRT-LLM
 
+
+FROM devel AS release
+WORKDIR /app
 COPY assets/ ./assets
 RUN wget -nc -P assets/ https://raw.githubusercontent.com/openai/whisper/main/whisper/assets/mel_filters.npz
 
@@ -22,7 +24,7 @@ RUN apt update && bash setup.sh && rm setup.sh
 
 COPY requirements/server.txt .
 RUN pip install --no-cache-dir -r server.txt && rm server.txt
-
+RUN pip install -U huggingface_hub tokenizers==0.19.0
 COPY whisper_live ./whisper_live
 COPY scripts/build_whisper_tensorrt.sh .
 COPY run_server.py .

requirements/server.txt

@@ -1,13 +1,13 @@
 faster-whisper==1.0.1
-torch==2.3.0
 websockets
 onnxruntime==1.16.0
 numba
-openai-whisper
 kaldialign
 soundfile
 ffmpeg-python
 scipy
 jiwer
 evaluate
-numpy<2
+numpy<2
+tiktoken==0.3.3
+openai-whisper