logo
docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2
linux/amd64 docker.io Xbox 贡献
12
浏览次数
20.59GB
镜像大小
国内镜像
swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2
源镜像
docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2
镜像ID
sha256:a0d1185315d19c85f77fcf816c10f23377e627dc3956a55f810c0e5f2088527b
镜像 TAG
v100-qwen38-flash-next-v5.2
镜像大小
20.59GB
平台架构
linux/amd64
镜像源
docker.io
CMD
/usr/local/bin/serve-qwen38
启动入口
/usr/local/bin/v100-entrypoint
工作目录
/opt/sglang
OS/平台
linux/amd64
镜像创建
2026-11-11T22:46:23.168827591+10:00
同步时间
2026-11-20 01:03
浏览量
12 次
贡献者
avatar Xbox
🔌 开放端口 1
8082/tcp
⚙️ 环境变量 67
KeyValue
PATH=/opt/venv/bin:/root/.cargo/bin:/usr/local/cuda/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin 0
NVARCH=x86_64 1
NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 2
NV_CUDA_CUDART_VERSION=12.8.90-1 3
CUDA_VERSION=12.8.1 4
LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib64 5
NVIDIA_VISIBLE_DEVICES=all 6
NVIDIA_DRIVER_CAPABILITIES=compute,utility 7
NV_CUDA_LIB_VERSION=12.8.1-1 8
NV_NVTX_VERSION=12.8.90-1 9
NV_LIBNPP_VERSION=12.3.3.100-1 10
NV_LIBNPP_PACKAGE=libnpp-12-8=12.3.3.100-1 11
NV_LIBCUSPARSE_VERSION=12.5.8.93-1 12
NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-8 13
NV_LIBCUBLAS_VERSION=12.8.4.1-1 14
NV_LIBCUBLAS_PACKAGE=libcublas-12-8=12.8.4.1-1 15
NV_LIBNCCL_PACKAGE_NAME=libnccl2 16
NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1 17
NCCL_VERSION=2.25.1-1 18
NV_LIBNCCL_PACKAGE=libnccl2=2.25.1-1+cuda12.8 19
NVIDIA_PRODUCT_NAME=CUDA 20
NV_CUDA_CUDART_DEV_VERSION=12.8.90-1 21
NV_NVML_DEV_VERSION=12.8.90-1 22
NV_LIBCUSPARSE_DEV_VERSION=12.5.8.93-1 23
NV_LIBNPP_DEV_VERSION=12.3.3.100-1 24
NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-8=12.3.3.100-1 25
NV_LIBCUBLAS_DEV_VERSION=12.8.4.1-1 26
NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-8 27
NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-8=12.8.4.1-1 28
NV_CUDA_NSIGHT_COMPUTE_VERSION=12.8.1-1 29
NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-8=12.8.1-1 30
NV_NVPROF_VERSION=12.8.90-1 31
NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-8=12.8.90-1 32
NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev 33
NV_LIBNCCL_DEV_PACKAGE_VERSION=2.25.1-1 34
NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.25.1-1+cuda12.8 35
LIBRARY_PATH=/usr/local/cuda/lib64/stubs 36
CUDA_HOME=/usr/local/cuda 37
CUDAHOSTCXX=/usr/bin/g++-12 38
TORCH_CUDA_ARCH_LIST=7.0 39
NVCC_THREADS=2 40
VIRTUAL_ENV=/opt/venv 41
NCCL_P2P_LEVEL=NVL 42
SGLANG_MAMBA_CONV_DTYPE=float16 43
SGLANG_MAMBA_SSM_DTYPE=float16 44
HF_HOME=/root/.cache/huggingface 45
FLASHINFER_WORKSPACE_BASE=/root/sglang-v100-jit 46
TILELANG_CACHE_DIR=/root/sglang-v100-jit/tilelang 47
TRITON_CACHE_DIR=/root/sglang-v100-jit/triton 48
TORCHINDUCTOR_CACHE_DIR=/root/sglang-v100-jit/torchinductor 49
SGLANG_V100_PYTHON=/opt/venv/bin/python 50
SGLANG_SM70_DENSE_GEMV=1 51
SGLANG_SM70_QWEN_FUSIONS=1 52
CXX=/usr/bin/g++-12 53
MAX_JOBS=2 54
SGLANG_PYTHON=/opt/venv/bin/python 55
PORT=8082 56
CUDA_VISIBLE_DEVICES=0,1,2,3 57
PYTHONUNBUFFERED=1 58
SGLANG_SM70_MTP_LOCAL_TOP1=0 59
SGLANG_SM70_HC_COMBINE_NORM=0 60
SGLANG_SM70_AR_PUSH16=0 61
SGLANG_MM_PREPROCESS_ON_CPU=1 62
TVM_FFI_CACHE_DIR=/root/sglang-v100-jit/tvm-ffi 63
TORCH_EXTENSIONS_DIR=/root/sglang-v100-jit/torch_extensions 64
SGLANG_V100_NVFP4_MOE_BUILD_DIR=/root/sglang-v100-jit/nvfp4_moe 65
SGLANG_V100_DECODE_CUDA_BUILD_DIR=/root/sglang-v100-jit/longctx_decode 66
🏷️ 镜像标签 5
KeyValue
NVIDIA CORPORATION <cudatools@nvidia.com> maintainer
ubuntu org.opencontainers.image.ref.name
75ff5f3cb5dc03480d8c2046928a00cb89ba53ba org.opencontainers.image.revision
SGLang Qwen3.8 Flash Next on V100 org.opencontainers.image.title
v100-qwen38-flash-next-v5.2 org.opencontainers.image.version

Docker拉取命令

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2  docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2  docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2

Shell快速替换命令

sed -i 's#geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2#' deployment.yaml

Ansible快速分发-Docker

#ansible k8s -m shell -a 'docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2  docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2  docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2'

镜像构建历史


# 2026-11-11 20:46:23  0.00B 设置默认要执行的命令
CMD ["/usr/local/bin/serve-qwen38"]
                        
# 2026-11-11 20:46:23  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/usr/local/bin/v100-entrypoint"]
                        
# 2026-11-11 20:46:23  0.00B 指定检查容器健康状态的命令
HEALTHCHECK &{["CMD-SHELL" "python -c 'import os,urllib.request; urllib.request.urlopen(\"http://127.0.0.1:\"+os.environ.get(\"PORT\",\"8082\")+\"/health\",timeout=3)'"] "30s" "5s" "1h0m0s" "0s" '\x03'}
                        
# 2026-11-11 20:46:23  0.00B 添加元数据标签
LABEL org.opencontainers.image.title=SGLang Qwen3.8 Flash Next on V100 org.opencontainers.image.version=v100-qwen38-flash-next-v5.2 org.opencontainers.image.revision=75ff5f3cb5dc03480d8c2046928a00cb89ba53ba
                        
# 2026-11-11 20:46:23  0.00B 定义构建参数
ARG SGLANG_SOURCE_REVISION=unknown
                        
# 2026-11-11 20:46:23  36.05MB 执行命令并创建新的镜像层
RUN /bin/sh -c python -m compileall -q /opt/sglang/python/sglang     && python -c 'import torch, flash_attn_v100; from sglang.srt.layers.attention.tilelang_fa_v100._grouped_qsa import load_grouped_qsa_ops; assert load_grouped_qsa_ops().sglang_masked_sparse_kv'     && for q38_script in /usr/local/bin/v100-entrypoint /opt/sglang/scripts/*qwen38*.sh; do bash -n "$q38_script" || exit; done     && chmod +x /usr/local/bin/v100-entrypoint /opt/sglang/scripts/serve_qwen38.sh /opt/sglang/scripts/qwen38.sh     && ln -s /opt/sglang/scripts/serve_qwen38.sh /usr/local/bin/serve-qwen38     && ln -s /opt/sglang/scripts/qwen38.sh /usr/local/bin/qwen38.sh # buildkit
                        
# 2026-11-11 20:46:00  224.00B 复制新文件或目录到容器中
COPY docker/v100-entrypoint.sh /usr/local/bin/v100-entrypoint # buildkit
                        
# 2026-11-11 20:46:00  24.03KB 复制新文件或目录到容器中
COPY scripts/serve_qwen38_flash_next_nvfp4_v100.sh scripts/serve_qwen38_flash_next_nvfp4_v100_mtp.sh scripts/serve_qwen38_flash_next_nvfp4_v100_throughput.sh scripts/serve_qwen38.sh scripts/qwen38.sh scripts/smoke_v100.sh /opt/sglang/scripts/ # buildkit
                        
# 2026-11-11 20:46:00  36.12MB 复制新文件或目录到容器中
COPY python/sglang /opt/sglang/python/sglang # buildkit
                        
# 2026-11-05 06:42:04  0.00B 执行命令并创建新的镜像层
RUN /bin/sh -c find /opt/sglang/python/sglang -type f ! -name '*.so' -delete # buildkit
                        
# 2026-11-05 06:42:03  208.27MB 执行命令并创建新的镜像层
RUN /bin/sh -c git clone https://github.com/ai-bond/flash-attention-v100.git /opt/deps/qwen38-vision     && git -C /opt/deps/qwen38-vision checkout --detach d89800edf608d85744f3ab6188be5fd0736acf39     && git -C /opt/deps/qwen38-vision apply       /opt/sglang/python/sglang/jit_kernel/third_party/flash_v100/vision_host_compat.patch     && git -C /opt/deps/qwen38-vision apply       /opt/sglang/python/sglang/jit_kernel/third_party/flash_v100/vision_container_build.patch     && MAX_JOBS=4 python -m pip install --no-deps --no-build-isolation /opt/deps/qwen38-vision # buildkit
                        
# 2026-11-05 06:33:14  58.66MB 执行命令并创建新的镜像层
RUN /bin/sh -c git clone --filter=blob:none --sparse --no-checkout       https://github.com/1CatAI/1Cat-vLLM.git /opt/deps/qwen38-grouped-qsa     && git -C /opt/deps/qwen38-grouped-qsa sparse-checkout set flash-attention-v100     && git -C /opt/deps/qwen38-grouped-qsa checkout --detach d8f42b391af06410ab01bb71657ededf7dce7799     && python /opt/sglang/scripts/setup_v100_grouped_qsa.py       --source /opt/deps/qwen38-grouped-qsa/flash-attention-v100       --build-dir /opt/deps/qwen38-grouped-qsa-build # buildkit
                        
# 2026-11-05 06:30:02  16.30KB 复制新文件或目录到容器中
COPY python/sglang/jit_kernel/third_party/flash_v100/grouped_masked_kv.patch python/sglang/jit_kernel/third_party/flash_v100/vision_host_compat.patch python/sglang/jit_kernel/third_party/flash_v100/vision_container_build.patch /opt/sglang/python/sglang/jit_kernel/third_party/flash_v100/ # buildkit
                        
# 2026-11-05 06:07:14  5.59KB 复制新文件或目录到容器中
COPY scripts/setup_v100_grouped_qsa.py /opt/sglang/scripts/ # buildkit
                        
# 2026-11-05 06:07:14  0.00B 设置环境变量 SGLANG_PYTHON PORT CUDA_VISIBLE_DEVICES PYTHONUNBUFFERED MAX_JOBS NVCC_THREADS CXX SGLANG_SM70_MTP_LOCAL_TOP1 SGLANG_SM70_HC_COMBINE_NORM SGLANG_SM70_AR_PUSH16 SGLANG_MM_PREPROCESS_ON_CPU TVM_FFI_CACHE_DIR TORCH_EXTENSIONS_DIR SGLANG_V100_NVFP4_MOE_BUILD_DIR SGLANG_V100_DECODE_CUDA_BUILD_DIR
ENV SGLANG_PYTHON=/opt/venv/bin/python PORT=8082 CUDA_VISIBLE_DEVICES=0,1,2,3 PYTHONUNBUFFERED=1 MAX_JOBS=2 NVCC_THREADS=2 CXX=/usr/bin/g++-12 SGLANG_SM70_MTP_LOCAL_TOP1=0 SGLANG_SM70_HC_COMBINE_NORM=0 SGLANG_SM70_AR_PUSH16=0 SGLANG_MM_PREPROCESS_ON_CPU=1 TVM_FFI_CACHE_DIR=/root/sglang-v100-jit/tvm-ffi TORCH_EXTENSIONS_DIR=/root/sglang-v100-jit/torch_extensions SGLANG_V100_NVFP4_MOE_BUILD_DIR=/root/sglang-v100-jit/nvfp4_moe SGLANG_V100_DECODE_CUDA_BUILD_DIR=/root/sglang-v100-jit/longctx_decode
                        
# 2026-09-09 06:28:59  35.96MB 执行命令并创建新的镜像层
RUN |1 SGLANG_SOURCE_REVISION=3b9bf5b0b043c8978b5a40cf3ffb113dc4724c2c /bin/sh -c python -m compileall -q /opt/sglang/python/sglang     && test -f /opt/sglang/python/sglang/jit_kernel/_sm70_marlin_v100_moe.abi3.so     && test -f /opt/sglang/python/sglang/jit_kernel/_sm70_marlin_v100_dense.abi3.so     && bash -n /opt/sglang/scripts/serve_qwen38_flash_next_nvfp4_v100.sh # buildkit
                        
# 2026-09-09 06:28:53  13.25KB 复制新文件或目录到容器中
COPY scripts/serve_qwen38_flash_next_nvfp4_v100.sh scripts/smoke_v100.sh /opt/sglang/scripts/ # buildkit
                        
# 2026-09-09 06:28:52  35.99MB 复制新文件或目录到容器中
COPY python/sglang /opt/sglang/python/sglang # buildkit
                        
# 2026-09-09 06:28:51  448.29MB 执行命令并创建新的镜像层
RUN |1 SGLANG_SOURCE_REVISION=3b9bf5b0b043c8978b5a40cf3ffb113dc4724c2c /bin/sh -c apt-get update     && apt-get install -y --no-install-recommends ffmpeg     && rm -rf /var/lib/apt/lists/*     && python -c 'from torchcodec.decoders import VideoDecoder' # buildkit
                        
# 2026-09-09 06:28:51  0.00B 设置环境变量 SGLANG_SM70_DENSE_GEMV SGLANG_SM70_QWEN_FUSIONS CXX MAX_JOBS
ENV SGLANG_SM70_DENSE_GEMV=1 SGLANG_SM70_QWEN_FUSIONS=1 CXX=/usr/bin/g++-12 MAX_JOBS=2
                        
# 2026-09-09 06:28:51  0.00B 添加元数据标签
LABEL org.opencontainers.image.title=SGLang Qwen3.8 Flash Next on V100 org.opencontainers.image.version=v100-qwen38-flash-next-v4 org.opencontainers.image.revision=3b9bf5b0b043c8978b5a40cf3ffb113dc4724c2c
                        
# 2026-09-09 06:28:51  0.00B 定义构建参数
ARG SGLANG_SOURCE_REVISION=3b9bf5b0b043c8978b5a40cf3ffb113dc4724c2c
                        
# 2026-08-31 12:08:33  5.43KB 执行命令并创建新的镜像层
RUN /bin/sh -c python -m py_compile /opt/sglang/python/sglang/srt/models/qwen4_exp_v100.py # buildkit
                        
# 2026-08-31 12:08:32  3.83KB 复制新文件或目录到容器中
COPY python/sglang/srt/models/qwen4_exp_v100.py /opt/sglang/python/sglang/srt/models/qwen4_exp_v100.py # buildkit
                        
# 2026-08-29 14:31:40  0.00B 设置默认要执行的命令
CMD ["--help"]
                        
# 2026-08-29 14:31:40  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/usr/local/bin/v100-entrypoint"]
                        
# 2026-08-29 14:31:40  0.00B 声明容器运行时监听的端口
EXPOSE map[8082/tcp:{}]
                        
# 2026-08-29 14:31:40  0.00B 设置工作目录为/opt/sglang
WORKDIR /opt/sglang
                        
# 2026-08-29 14:31:40  11.56KB 执行命令并创建新的镜像层
RUN /bin/sh -c chmod +x /opt/sglang/scripts/smoke_v100.sh /usr/local/bin/v100-entrypoint # buildkit
                        
# 2026-08-29 14:31:40  224.00B 复制新文件或目录到容器中
COPY docker/v100-entrypoint.sh /usr/local/bin/v100-entrypoint # buildkit
                        
# 2026-08-29 14:31:40  11.34KB 复制新文件或目录到容器中
COPY scripts/smoke_v100.sh /opt/sglang/scripts/smoke_v100.sh # buildkit
                        
# 2026-08-29 14:31:40  708.74MB 复制新文件或目录到容器中
COPY /opt/sglang/python /opt/sglang/python # buildkit
                        
# 2026-08-29 14:31:34  45.56MB 复制新文件或目录到容器中
COPY /opt/deps/flashinfer-sm70 /opt/deps/flashinfer-sm70 # buildkit
                        
# 2026-08-29 14:31:34  9.17GB 复制新文件或目录到容器中
COPY /opt/venv /opt/venv # buildkit
                        
# 2026-08-29 09:19:50  0.00B 设置环境变量 NCCL_P2P_LEVEL SGLANG_MAMBA_CONV_DTYPE SGLANG_MAMBA_SSM_DTYPE HF_HOME FLASHINFER_WORKSPACE_BASE TILELANG_CACHE_DIR TRITON_CACHE_DIR TORCHINDUCTOR_CACHE_DIR SGLANG_V100_PYTHON
ENV NCCL_P2P_LEVEL=NVL SGLANG_MAMBA_CONV_DTYPE=float16 SGLANG_MAMBA_SSM_DTYPE=float16 HF_HOME=/root/.cache/huggingface FLASHINFER_WORKSPACE_BASE=/root/sglang-v100-jit TILELANG_CACHE_DIR=/root/sglang-v100-jit/tilelang TRITON_CACHE_DIR=/root/sglang-v100-jit/triton TORCHINDUCTOR_CACHE_DIR=/root/sglang-v100-jit/torchinductor SGLANG_V100_PYTHON=/opt/venv/bin/python
                        
# 2026-08-29 09:19:50  406.79MB 执行命令并创建新的镜像层
RUN |1 DEBIAN_FRONTEND=noninteractive /bin/sh -c apt-get update && apt-get install -y --no-install-recommends       build-essential ca-certificates cmake curl git g++-12 libnuma-dev       ninja-build patch pkg-config protobuf-compiler python3.12 python3.12-dev       python3-pip python3-venv     && ln -sf /usr/bin/python3.12 /usr/local/bin/python     && ln -sf /usr/bin/python3.12 /usr/local/bin/python3     && python -m venv "$VIRTUAL_ENV" # buildkit
                        
# 2026-08-29 09:19:50  0.00B 设置环境变量 CUDA_HOME CUDAHOSTCXX TORCH_CUDA_ARCH_LIST NVCC_THREADS VIRTUAL_ENV PATH LD_LIBRARY_PATH
ENV CUDA_HOME=/usr/local/cuda CUDAHOSTCXX=/usr/bin/g++-12 TORCH_CUDA_ARCH_LIST=7.0 NVCC_THREADS=1 VIRTUAL_ENV=/opt/venv PATH=/opt/venv/bin:/root/.cargo/bin:/usr/local/cuda/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib64
                        
# 2026-08-29 09:19:50  0.00B 定义构建参数
ARG DEBIAN_FRONTEND=noninteractive
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs
                        
# 2025-03-11 06:44:37  390.89KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_DEV_PACKAGE_NAME} ${NV_LIBNCCL_DEV_PACKAGE_NAME} # buildkit
                        
# 2025-03-11 06:44:37  5.99GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-cudart-dev-12-8=${NV_CUDA_CUDART_DEV_VERSION}     cuda-command-line-tools-12-8=${NV_CUDA_LIB_VERSION}     cuda-minimal-build-12-8=${NV_CUDA_LIB_VERSION}     cuda-libraries-dev-12-8=${NV_CUDA_LIB_VERSION}     cuda-nvml-dev-12-8=${NV_NVML_DEV_VERSION}     ${NV_NVPROF_DEV_PACKAGE}     ${NV_LIBNPP_DEV_PACKAGE}     libcusparse-dev-12-8=${NV_LIBCUSPARSE_DEV_VERSION}     ${NV_LIBCUBLAS_DEV_PACKAGE}     ${NV_LIBNCCL_DEV_PACKAGE}     ${NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-03-11 06:44:37  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-03-11 06:44:37  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE
ENV NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.25.1-1+cuda12.8
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.25.1-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_VERSION
ENV NV_LIBNCCL_DEV_PACKAGE_VERSION=2.25.1-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_NAME
ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_NVPROF_DEV_PACKAGE
ENV NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-8=12.8.90-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_NVPROF_VERSION
ENV NV_NVPROF_VERSION=12.8.90-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE
ENV NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-8=12.8.1-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_VERSION
ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=12.8.1-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE
ENV NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-8=12.8.4.1-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE_NAME
ENV NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-8
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_VERSION
ENV NV_LIBCUBLAS_DEV_VERSION=12.8.4.1-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBNPP_DEV_PACKAGE
ENV NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-8=12.3.3.100-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBNPP_DEV_VERSION
ENV NV_LIBNPP_DEV_VERSION=12.3.3.100-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_LIBCUSPARSE_DEV_VERSION
ENV NV_LIBCUSPARSE_DEV_VERSION=12.5.8.93-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_NVML_DEV_VERSION
ENV NV_NVML_DEV_VERSION=12.8.90-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_CUDA_CUDART_DEV_VERSION
ENV NV_CUDA_CUDART_DEV_VERSION=12.8.90-1
                        
# 2025-03-11 06:44:37  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.8.1-1
                        
# 2025-03-11 06:30:18  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2025-03-11 06:30:18  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2025-03-11 06:30:18  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2025-03-11 06:30:18  239.89KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit
                        
# 2025-03-11 06:30:18  3.11GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-libraries-12-8=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-12-8=${NV_NVTX_VERSION}     libcusparse-12-8=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     ${NV_LIBNCCL_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-03-11 06:30:18  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-03-11 06:30:18  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.25.1-1+cuda12.8
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.25.1-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-8=12.8.4.1-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.8.4.1-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-8
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.5.8.93-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-8=12.3.3.100-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.3.3.100-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.8.90-1
                        
# 2025-03-11 06:30:18  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.8.1-1
                        
# 2025-03-11 06:19:21  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2025-03-11 06:19:21  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2025-03-11 06:19:21  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2025-03-11 06:19:21  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64
                        
# 2025-03-11 06:19:21  0.00B 设置环境变量 PATH
ENV PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
                        
# 2025-03-11 06:19:21  22.00B 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
                        
# 2025-03-11 06:19:21  203.31MB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-cudart-12-8=${NV_CUDA_CUDART_VERSION}     cuda-compat-12-8     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-03-11 06:19:07  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.8.1
                        
# 2025-03-11 06:19:07  16.75MB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     gnupg2 curl ca-certificates &&     curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - &&     echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list &&     apt-get purge --autoremove -y curl     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-03-11 06:19:07  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-03-11 06:19:07  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-03-11 06:19:07  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.8.90-1
                        
# 2025-03-11 06:19:07  0.00B 设置环境变量 NVIDIA_REQUIRE_CUDA brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand
ENV NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566
                        
# 2025-03-11 06:19:07  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2025-01-27 12:14:03  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2025-01-27 12:14:03  78.13MB 
/bin/sh -c #(nop) ADD file:6df775300d76441aa33f31b22c1afce8dfe35c8ffbc14ef27c27009235b12a95 in / 
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=24.04
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  ARG RELEASE
                        
                    

镜像信息

{
    "Id": "sha256:a0d1185315d19c85f77fcf816c10f23377e627dc3956a55f810c0e5f2088527b",
    "RepoTags": [
        "geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2"
    ],
    "RepoDigests": [
        "geesegeesegeese/sglang-v100@sha256:28cc3e7f951e4331a1fd6ad0b140863ca84ed602c1be5e1b91f9f1f3b91dd496",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/geesegeesegeese/sglang-v100@sha256:df524cf558911b816787c0501914d99a9251dc60d338919d69bb5544d694fc97"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2026-11-11T22:46:23.168827591+10:00",
    "Container": "",
    "ContainerConfig": null,
    "DockerVersion": "",
    "Author": "",
    "Config": {
        "Hostname": "",
        "Domainname": "",
        "User": "",
        "AttachStdin": false,
        "AttachStdout": false,
        "AttachStderr": false,
        "ExposedPorts": {
            "8082/tcp": {}
        },
        "Tty": false,
        "OpenStdin": false,
        "StdinOnce": false,
        "Env": [
            "PATH=/opt/venv/bin:/root/.cargo/bin:/usr/local/cuda/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
            "NVARCH=x86_64",
            "NVIDIA_REQUIRE_CUDA=cuda\u003e=12.8 brand=unknown,driver\u003e=470,driver\u003c471 brand=grid,driver\u003e=470,driver\u003c471 brand=tesla,driver\u003e=470,driver\u003c471 brand=nvidia,driver\u003e=470,driver\u003c471 brand=quadro,driver\u003e=470,driver\u003c471 brand=quadrortx,driver\u003e=470,driver\u003c471 brand=nvidiartx,driver\u003e=470,driver\u003c471 brand=vapps,driver\u003e=470,driver\u003c471 brand=vpc,driver\u003e=470,driver\u003c471 brand=vcs,driver\u003e=470,driver\u003c471 brand=vws,driver\u003e=470,driver\u003c471 brand=cloudgaming,driver\u003e=470,driver\u003c471 brand=unknown,driver\u003e=535,driver\u003c536 brand=grid,driver\u003e=535,driver\u003c536 brand=tesla,driver\u003e=535,driver\u003c536 brand=nvidia,driver\u003e=535,driver\u003c536 brand=quadro,driver\u003e=535,driver\u003c536 brand=quadrortx,driver\u003e=535,driver\u003c536 brand=nvidiartx,driver\u003e=535,driver\u003c536 brand=vapps,driver\u003e=535,driver\u003c536 brand=vpc,driver\u003e=535,driver\u003c536 brand=vcs,driver\u003e=535,driver\u003c536 brand=vws,driver\u003e=535,driver\u003c536 brand=cloudgaming,driver\u003e=535,driver\u003c536 brand=unknown,driver\u003e=550,driver\u003c551 brand=grid,driver\u003e=550,driver\u003c551 brand=tesla,driver\u003e=550,driver\u003c551 brand=nvidia,driver\u003e=550,driver\u003c551 brand=quadro,driver\u003e=550,driver\u003c551 brand=quadrortx,driver\u003e=550,driver\u003c551 brand=nvidiartx,driver\u003e=550,driver\u003c551 brand=vapps,driver\u003e=550,driver\u003c551 brand=vpc,driver\u003e=550,driver\u003c551 brand=vcs,driver\u003e=550,driver\u003c551 brand=vws,driver\u003e=550,driver\u003c551 brand=cloudgaming,driver\u003e=550,driver\u003c551 brand=unknown,driver\u003e=560,driver\u003c561 brand=grid,driver\u003e=560,driver\u003c561 brand=tesla,driver\u003e=560,driver\u003c561 brand=nvidia,driver\u003e=560,driver\u003c561 brand=quadro,driver\u003e=560,driver\u003c561 brand=quadrortx,driver\u003e=560,driver\u003c561 brand=nvidiartx,driver\u003e=560,driver\u003c561 brand=vapps,driver\u003e=560,driver\u003c561 brand=vpc,driver\u003e=560,driver\u003c561 brand=vcs,driver\u003e=560,driver\u003c561 brand=vws,driver\u003e=560,driver\u003c561 brand=cloudgaming,driver\u003e=560,driver\u003c561 brand=unknown,driver\u003e=565,driver\u003c566 brand=grid,driver\u003e=565,driver\u003c566 brand=tesla,driver\u003e=565,driver\u003c566 brand=nvidia,driver\u003e=565,driver\u003c566 brand=quadro,driver\u003e=565,driver\u003c566 brand=quadrortx,driver\u003e=565,driver\u003c566 brand=nvidiartx,driver\u003e=565,driver\u003c566 brand=vapps,driver\u003e=565,driver\u003c566 brand=vpc,driver\u003e=565,driver\u003c566 brand=vcs,driver\u003e=565,driver\u003c566 brand=vws,driver\u003e=565,driver\u003c566 brand=cloudgaming,driver\u003e=565,driver\u003c566",
            "NV_CUDA_CUDART_VERSION=12.8.90-1",
            "CUDA_VERSION=12.8.1",
            "LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.8.1-1",
            "NV_NVTX_VERSION=12.8.90-1",
            "NV_LIBNPP_VERSION=12.3.3.100-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-8=12.3.3.100-1",
            "NV_LIBCUSPARSE_VERSION=12.5.8.93-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-8",
            "NV_LIBCUBLAS_VERSION=12.8.4.1-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-12-8=12.8.4.1-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1",
            "NCCL_VERSION=2.25.1-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.25.1-1+cuda12.8",
            "NVIDIA_PRODUCT_NAME=CUDA",
            "NV_CUDA_CUDART_DEV_VERSION=12.8.90-1",
            "NV_NVML_DEV_VERSION=12.8.90-1",
            "NV_LIBCUSPARSE_DEV_VERSION=12.5.8.93-1",
            "NV_LIBNPP_DEV_VERSION=12.3.3.100-1",
            "NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-8=12.3.3.100-1",
            "NV_LIBCUBLAS_DEV_VERSION=12.8.4.1-1",
            "NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-8",
            "NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-8=12.8.4.1-1",
            "NV_CUDA_NSIGHT_COMPUTE_VERSION=12.8.1-1",
            "NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-8=12.8.1-1",
            "NV_NVPROF_VERSION=12.8.90-1",
            "NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-8=12.8.90-1",
            "NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev",
            "NV_LIBNCCL_DEV_PACKAGE_VERSION=2.25.1-1",
            "NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.25.1-1+cuda12.8",
            "LIBRARY_PATH=/usr/local/cuda/lib64/stubs",
            "CUDA_HOME=/usr/local/cuda",
            "CUDAHOSTCXX=/usr/bin/g++-12",
            "TORCH_CUDA_ARCH_LIST=7.0",
            "NVCC_THREADS=2",
            "VIRTUAL_ENV=/opt/venv",
            "NCCL_P2P_LEVEL=NVL",
            "SGLANG_MAMBA_CONV_DTYPE=float16",
            "SGLANG_MAMBA_SSM_DTYPE=float16",
            "HF_HOME=/root/.cache/huggingface",
            "FLASHINFER_WORKSPACE_BASE=/root/sglang-v100-jit",
            "TILELANG_CACHE_DIR=/root/sglang-v100-jit/tilelang",
            "TRITON_CACHE_DIR=/root/sglang-v100-jit/triton",
            "TORCHINDUCTOR_CACHE_DIR=/root/sglang-v100-jit/torchinductor",
            "SGLANG_V100_PYTHON=/opt/venv/bin/python",
            "SGLANG_SM70_DENSE_GEMV=1",
            "SGLANG_SM70_QWEN_FUSIONS=1",
            "CXX=/usr/bin/g++-12",
            "MAX_JOBS=2",
            "SGLANG_PYTHON=/opt/venv/bin/python",
            "PORT=8082",
            "CUDA_VISIBLE_DEVICES=0,1,2,3",
            "PYTHONUNBUFFERED=1",
            "SGLANG_SM70_MTP_LOCAL_TOP1=0",
            "SGLANG_SM70_HC_COMBINE_NORM=0",
            "SGLANG_SM70_AR_PUSH16=0",
            "SGLANG_MM_PREPROCESS_ON_CPU=1",
            "TVM_FFI_CACHE_DIR=/root/sglang-v100-jit/tvm-ffi",
            "TORCH_EXTENSIONS_DIR=/root/sglang-v100-jit/torch_extensions",
            "SGLANG_V100_NVFP4_MOE_BUILD_DIR=/root/sglang-v100-jit/nvfp4_moe",
            "SGLANG_V100_DECODE_CUDA_BUILD_DIR=/root/sglang-v100-jit/longctx_decode"
        ],
        "Cmd": [
            "/usr/local/bin/serve-qwen38"
        ],
        "Healthcheck": {
            "Test": [
                "CMD-SHELL",
                "python -c 'import os,urllib.request; urllib.request.urlopen(\"http://127.0.0.1:\"+os.environ.get(\"PORT\",\"8082\")+\"/health\",timeout=3)'"
            ],
            "Interval": 30000000000,
            "Timeout": 5000000000,
            "StartPeriod": 3600000000000,
            "Retries": 3
        },
        "ArgsEscaped": true,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/opt/sglang",
        "Entrypoint": [
            "/usr/local/bin/v100-entrypoint"
        ],
        "OnBuild": null,
        "Labels": {
            "maintainer": "NVIDIA CORPORATION \u003ccudatools@nvidia.com\u003e",
            "org.opencontainers.image.ref.name": "ubuntu",
            "org.opencontainers.image.revision": "75ff5f3cb5dc03480d8c2046928a00cb89ba53ba",
            "org.opencontainers.image.title": "SGLang Qwen3.8 Flash Next on V100",
            "org.opencontainers.image.version": "v100-qwen38-flash-next-v5.2"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 20586522149,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/1ed07ee9d79403019e82f6cf938d6e4e58e491398b0a24624d5bb22d83885ad4/diff:/var/lib/docker/overlay2/8ce8c04fe9b8d188073f5c54836e74f550f8ff186d0544cdf6a597e23a3daba7/diff:/var/lib/docker/overlay2/096e9bdbbe88157763acf917e2f8aa5686d4763d445088f817381516cb39c72d/diff:/var/lib/docker/overlay2/84b5c695de1bc2423880fdfd4a1095ec176bda24785fe5f0facafd228a6ea57a/diff:/var/lib/docker/overlay2/bc445a208190ee71cc98a13462995a0d3bf003a96e4062bd8b79726c3f9bd1b0/diff:/var/lib/docker/overlay2/b0fe698ea78f2248e748aabd2f5b20c88b403b5c7b02b3a8dd80a88d996b7362/diff:/var/lib/docker/overlay2/42bd1cf1a9746888d4a04bdf4e0047513cb92ccd6e5e3f2aa43a6f144f350db9/diff:/var/lib/docker/overlay2/bfe73cc3a9762105bc3e91f4df23bab69f75d42a65bceb985792ba5421f2a1ef/diff:/var/lib/docker/overlay2/0d850fd47d5ada1b9a80f69bc40d306e5accb4b0335be550b216561a2c37f894/diff:/var/lib/docker/overlay2/7252fb6b20e4a15d16c024b499b1d0f377e1e2ad31fc161622532a988fdacccc/diff:/var/lib/docker/overlay2/2e6ab624a78a97e47eafb15014d1becc2e76ab530be98199b3a2e61d60089d01/diff:/var/lib/docker/overlay2/1f1d98b878c4289823bfcaaf6aff6471f7e757c64e5242dfcdf1f1d340104d06/diff:/var/lib/docker/overlay2/cff3317cb4e8239110033c7cbfc0817e952149374401a61ad4e98419dc0fd3cb/diff:/var/lib/docker/overlay2/69a48e9f0e240ec2689e4f736e2e152f9fe7beb76b36fe738ef017583060c71b/diff:/var/lib/docker/overlay2/7fbea8f7712a064f5a25fa7be6748e3c18ad065642d6a81ccc30b7042d43eced/diff:/var/lib/docker/overlay2/63aab775366b7de3345a2034aed0c7892b1adea85d093b304efa2049f4d1d398/diff:/var/lib/docker/overlay2/19e744569650c41e619e23e5b1f7b380fff68f94263bbb350d72a77eea2fb81e/diff:/var/lib/docker/overlay2/f71220535049f31b6a8e5b3fb5f5277c8570931cccae2262122b1febfcb03c5a/diff:/var/lib/docker/overlay2/ef5e84202381200c05e32f90d1bbdc11914b0527be964b0c74ab81ab2d41b380/diff:/var/lib/docker/overlay2/cdc3855b146c9d0691bddf0ee4d0491a3bed328e1b350bdb15db148bed30084a/diff:/var/lib/docker/overlay2/074ea303f6cb57734111feda9329b41c0474e70c19c72b64636c7bc8a8967196/diff:/var/lib/docker/overlay2/7ef195b17859fc743ce945ec7b2e640ce9e14ca14532222e3a0013c04ad4318a/diff:/var/lib/docker/overlay2/7bac5aa2e61f1e482e96bcbd5046698bd2d9b322a9de883f4f8ff0ecae1245f7/diff:/var/lib/docker/overlay2/ef1d107736779ea97aa8ca31ccdc884f0a251803cf9aae0345605ef4a658cdc8/diff:/var/lib/docker/overlay2/abf086a57f8782ecc569e37673c4e90f5d13a454a22a0f34ba64a691eb8c197b/diff:/var/lib/docker/overlay2/b52583bd6d26739393144db533cb6d43c496a7140423fbad7b3c34af9ae2726b/diff:/var/lib/docker/overlay2/d0497a64fff473eda27d2a04fe284f9504156e0988acc504a4759e77ad21c3bf/diff:/var/lib/docker/overlay2/a2eac99e035a8c9ec651ee2649d39b7ee11e50930489ed3d3496f1ec233a4bea/diff:/var/lib/docker/overlay2/260bb0c6dad93c7a262f94287be54ccf1cdee7f078c65fda582790c1f4617910/diff:/var/lib/docker/overlay2/5ccc1b54f7a51b496b49da13b01d33fe558baea16ae5d5cf17ff9357371791fd/diff:/var/lib/docker/overlay2/8da6da8fe2b00f16041ddb2c09d4c9186ad0a4a256f7507eca05f65382b0d809/diff:/var/lib/docker/overlay2/c2d741c3a1be29cbb3b252196454499ad81ec4f22e6b6df1717a793f1aed796c/diff:/var/lib/docker/overlay2/19fffd52065d75868fdbbb6be3592234533522121dc373ebacf0196b340a0329/diff",
            "MergedDir": "/var/lib/docker/overlay2/ce0cf55897c1e23046877d79b62bffdb467b82bc213ead97edac410c538556c4/merged",
            "UpperDir": "/var/lib/docker/overlay2/ce0cf55897c1e23046877d79b62bffdb467b82bc213ead97edac410c538556c4/diff",
            "WorkDir": "/var/lib/docker/overlay2/ce0cf55897c1e23046877d79b62bffdb467b82bc213ead97edac410c538556c4/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:4b7c01ed0534d4f9be9cf97d068da1598c6c20b26cb6134fad066defdb6d541d",
            "sha256:5d874d849ec64ad89b8e1ff34cefc562238dfaaa6540905f0a8bac73777d4f25",
            "sha256:5ef6645238f3599acf1a7b450ae0a8e9306bea4e342a7af89d3992b804676999",
            "sha256:723554db4ba2a109baacf03b25cff50db586ce45370dfdbd21557171201992f5",
            "sha256:6020d84069cf575521faca653d2817e2195b8233b8c4e2d7bc65f3296296c2bb",
            "sha256:09d8fc1b386fa3eb8491421932e290ce3c33a55265e1d6da8cc9d720a08d3306",
            "sha256:d9ab1aaed362889c6b77ea27e8df132379e24e2a0aacdfaed8fadf3cddb3131d",
            "sha256:9004b01e4a91e9612a7374cce04c721e1e3a8f9e99619de547fb333425c79637",
            "sha256:a2dd2dc8d2b5463fe695696cc9b429d90af7bb8b1ad911859146a38b720f4963",
            "sha256:ac5865c2298fb29741c8243c732ce3eda6c4bf96f3f571cfc0fd4fb800c0a2ea",
            "sha256:ed18f36cfec73e644207a28dc46967159c8307e8afcf2c3bc34ab2e27e2db271",
            "sha256:dea0f2f4ad4f8d48afa210cd62a4425717cd07bec5e129661a75f6178b6ee826",
            "sha256:a7a44c2b1b95099f2aa805c490552e4b3947843edd4027aa9725e026fcf6a72c",
            "sha256:91528d1e3386340c324f45abff7a4b85e26c5c8a0e9b01fc033be570a319799f",
            "sha256:61cfafdf971909bdba90818d226d5595f7ac295b00c6eceeaae61fe8284e9d3d",
            "sha256:5b479875157db2faee129c62b7a3a53b6148869acfdb0dee1182c5054a5d91cc",
            "sha256:31bf19eacfc89cdc65a8d6a7966d1f076c9fd63b0eefda8dc3505aa8a764c755",
            "sha256:b1e0efbea80220f1625eeb656705d24a23f01a011a3ca235deaf8b7c353acefb",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:88762d72731c18788f71b7e942f89e1cc4d2865fc67e64a94196c66ef5baa5f6",
            "sha256:7c4099a9ae4943f8a4c2459edef8e2a0c28508b10676696e025dcc2fb473e69e",
            "sha256:945a39fe8bd051a602dee6db7afe5a0c20605cd763ba0e23f23a803f351952d2",
            "sha256:d90e58fdec93788787f0f4944a472e49ba6f72e80844eae2ae108296e872a305",
            "sha256:97a31317d1a20ce715f3e18696123af6c67df22927693904ade948058820aa4c",
            "sha256:6786594cd7ea250459c43091081f46326f1bfb5e933fae303cef60eccb018c68",
            "sha256:f3732ce66c7dd7b312efbdf54a199e98a06082cdc65d8f0dcdd313b5388c2806",
            "sha256:89f2cfc412379672085899a0c81df7298ba2e49ff2b8b4f2f2e9324660890928",
            "sha256:20014f1f65ec67242350ab7f531a491c04f782c491d1dea3e270b1f9991f9018",
            "sha256:744515c2167ddc7e9a3e1a1044fee2861087e9b8c46de2cd75ddc2e8bb99decf",
            "sha256:26057cf35fb2c39b7b1bccf47394282543dc503b96a942ed83df8e5bc514351b",
            "sha256:5ba6f536777c61cf1f5d93994c18d7ed714e8d18bf89abd514b33d10b575c1fd",
            "sha256:5c4fd5aeaf7911cc2af7da4b74648e63966ca0653c0b99e5680040f8bebc9b3b",
            "sha256:4b013b9d55cac58a8900f97e13e27b46034637f04ca6a30f8a1ccd69fa4296e4",
            "sha256:4901aa85adf33b2c98d4da824401c98c5bf1e07eb3d528512777970f6c09bd77"
        ]
    },
    "Metadata": {
        "LastTagTime": "2026-11-20T00:54:55.472339422+08:00"
    }
}

更多版本

docker.io/geesegeesegeese/sglang-v100:v100-qwen38-flash-next-v5.2

linux/amd64 docker.io20.59GB2026-11-20 01:03
11
检测到您正在使用广告拦截插件,本站为公益站点,依赖广告维持运转 🙏 查看如何关闭 ×