cjones/WhisperLive
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Upgrade tensorrt_llm to 0.15.0

Browse Source 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
This commit is contained in:
makaveli10
2024-11-21 06:13:00 +00:00
parent 446fc6e835
commit c25a036c02
5 changed files with 218 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker/Dockerfile.tensorrt
+5 -5
View File
@@ -1,15 +1,16 @@
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04 AS base
FROM nvidia/cuda:12.5.1-runtime-ubuntu22.04 AS base
ARG DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y \
python3.10 python3-pip openmpi-bin libopenmpi-dev git wget \
python3.10 python3-pip openmpi-bin libopenmpi-dev git git-lfs wget \
&& rm -rf /var/lib/apt/lists/*
FROM base AS devel
RUN pip3 install --no-cache-dir -U tensorrt_llm==0.10.0 --extra-index-url https://pypi.nvidia.com
RUN pip3 install --no-cache-dir -U tensorrt_llm==0.15.0.dev2024111200 --extra-index-url https://pypi.nvidia.com
WORKDIR /app
RUN git clone -b v0.10.0 --depth 1 https://github.com/NVIDIA/TensorRT-LLM.git && \
RUN git clone --depth 1 https://github.com/NVIDIA/TensorRT-LLM.git && cd TensorRT-LLM && \
git checkout c629546ce429623c8a163633095230154a6f0574 && cd ../ && \
mv TensorRT-LLM/examples ./TensorRT-LLM-examples && \
rm -rf TensorRT-LLM
@@ -24,7 +25,6 @@ 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 .