x

Dockerfile

@@ -19,22 +19,15 @@ ARG GFX=gfx120X-all
 RUN set -euo pipefail; \
   BASE="https://therock-nightly-tarball.s3.amazonaws.com"; \
   PREFIX="therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}"; \
-  echo "Fetching file list from ${BASE}..."; \
-  KEY="$(curl -x socks5://192.168.0.11:1080 -s "${BASE}?list-type=2&prefix=${PREFIX}" \
+  KEY="$(proxychains curl -s "${BASE}?list-type=2&prefix=${PREFIX}" \
   | tr '<' '\n' \
   | grep -o "therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}\..*\.tar\.gz" \
   | sort -V | tail -n1)"; \
-  if [ -z "$KEY" ]; then \
-    echo "ERROR: Failed to get tarball filename"; \
-    exit 1; \
-  fi; \
   echo "Downloading Latest Tarball: ${KEY}"; \
-  curl -x socks5://192.168.0.11:1080 -L -o therock.tar.gz "${BASE}/${KEY}" || { echo "ERROR: Download failed"; exit 1; }; \
-  echo "Extracting tarball..."; \
+  proxychains aria2c -x 16 -s 16 -j 16 --file-allocation=none "${BASE}/${KEY}" -o therock.tar.gz; \
   mkdir -p /opt/rocm; \
-  tar xzf therock.tar.gz -C /opt/rocm --strip-components=1 || { echo "ERROR: Extraction failed"; exit 1; }; \
-  rm therock.tar.gz; \
-  echo "ROCm SDK installed successfully"
+  tar xzf therock.tar.gz -C /opt/rocm --strip-components=1; \
+  rm therock.tar.gz
 
 # 3. Configure Global ROCm Environment
 RUN export ROCM_PATH=/opt/rocm && \
@@ -74,9 +67,9 @@ RUN proxychains python -m pip install \
 WORKDIR /opt
 ENV FLASH_ATTENTION_TRITON_AMD_ENABLE="TRUE"
 
-RUN proxychains git clone https://github.com/ROCm/flash-attention.git &&\
-  cd flash-attention &&\
-  git checkout main_perf &&\
+RUN proxychains git clone https://github.com/ROCm/flash-attention.git && \
+  cd flash-attention && \
+  git checkout main_perf && \
   python setup.py install && \
   cd /opt && rm -rf /opt/flash-attention
 
@@ -85,11 +78,8 @@ RUN proxychains git clone https://github.com/vllm-project/vllm.git /opt/vllm
 WORKDIR /opt/vllm
 
 # --- PATCHING ---
-# vLLM relies on 'amdsmi' to detect AMD GPUs. If it's missing or fails (common in containers),
-# vLLM falls back to CPU. We patch it to force ROCm detection.
 RUN echo "import sys, re" > patch_vllm.py && \
   echo "from pathlib import Path" >> patch_vllm.py && \
-  # Patch 1: __init__.py - Force is_rocm=True and bypass amdsmi checks
   echo "p = Path('vllm/platforms/__init__.py')" >> patch_vllm.py && \
   echo "txt = p.read_text()" >> patch_vllm.py && \
   echo "txt = txt.replace('import amdsmi', '# import amdsmi')" >> patch_vllm.py && \
@@ -98,7 +88,6 @@ RUN echo "import sys, re" > patch_vllm.py && \
   echo "txt = txt.replace('amdsmi.amdsmi_init()', 'pass')" >> patch_vllm.py && \
   echo "txt = txt.replace('amdsmi.amdsmi_shut_down()', 'pass')" >> patch_vllm.py && \
   echo "p.write_text(txt)" >> patch_vllm.py && \
-  # Patch 2: rocm.py - Mock amdsmi and force device name
   echo "p = Path('vllm/platforms/rocm.py')" >> patch_vllm.py && \
   echo "txt = p.read_text()" >> patch_vllm.py && \
   echo "header = 'import sys\nfrom unittest.mock import MagicMock\nsys.modules[\"amdsmi\"] = MagicMock()\n'" >> patch_vllm.py && \
@@ -110,19 +99,16 @@ RUN echo "import sys, re" > patch_vllm.py && \
   echo "print('Successfully patched vLLM for R9700')" >> patch_vllm.py && \
   python patch_vllm.py
 
-# 7. Build vLLM (Wheel Method) with CLANG Host Compiler
+# 7. Build vLLM
 RUN python -m pip install --upgrade cmake ninja packaging wheel numpy "setuptools-scm>=8" "setuptools<80.0.0" scikit-build-core pybind11
 ENV ROCM_HOME="/opt/rocm"
 ENV HIP_PATH="/opt/rocm"
 ENV VLLM_TARGET_DEVICE="rocm"
 ENV PYTORCH_ROCM_ARCH="gfx1201"
-ENV HIP_ARCHITECTURES="gfx1201"          
-ENV AMDGPU_TARGETS="gfx1201"              
+ENV HIP_ARCHITECTURES="gfx1201"
+ENV AMDGPU_TARGETS="gfx1201"
 ENV MAX_JOBS="32"
 
-# --- FIX FOR SEGFAULT ---
-# We force the Host Compiler (CC/CXX) to be the ROCm Clang, not Fedora GCC.
-# This aligns the ABI of the compiled vLLM extensions with PyTorch.
 ENV CC="/opt/rocm/llvm/bin/clang"
 ENV CXX="/opt/rocm/llvm/bin/clang++"
 
@@ -133,16 +119,14 @@ RUN export HIP_DEVICE_LIB_PATH=$(find /opt/rocm -type d -name bitcode -print -qu
   python -m pip wheel --no-build-isolation --no-deps -w /tmp/dist -v . && \
   python -m pip install /tmp/dist/*.whl
 
-# --- bitsandbytes (ROCm) ---
+# bitsandbytes
 WORKDIR /opt
 RUN proxychains git clone -b rocm_enabled_multi_backend https://github.com/ROCm/bitsandbytes.git
 WORKDIR /opt/bitsandbytes
 
-# Explicitly set HIP_PLATFORM (Docker ENV, not /etc/profile)
 ENV HIP_PLATFORM="amd"
 ENV CMAKE_PREFIX_PATH="/opt/rocm"
 
-# Force CMake to use the System ROCm Compiler (/opt/rocm/llvm/bin/clang++)
 RUN cmake -S . \
   -DGPU_TARGETS="gfx1201" \
   -DBNB_ROCM_ARCH="gfx1201" \
@@ -153,7 +137,7 @@ RUN cmake -S . \
   make -j$(nproc) && \
   python -m pip install --no-cache-dir . --no-build-isolation --no-deps
 
-# 8. Final Cleanup & Runtime
+# Cleanup
 WORKDIR /opt
 RUN chmod -R a+rwX /opt && \
   find /opt/venv -type f -name "*.so" -exec strip -s {} + 2>/dev/null || true && \
@@ -161,11 +145,8 @@ RUN chmod -R a+rwX /opt && \
   rm -rf /root/.cache/pip || true && \
   dnf clean all && rm -rf /var/cache/dnf/*
 
-# Create vLLM configuration directory and model directory
-RUN mkdir -p /etc/vllm && \
-  mkdir -p /model
+RUN mkdir -p /etc/vllm && mkdir -p /model
 
-# Copy necessary scripts
 COPY scripts/01-rocm-envs.sh /etc/profile.d/01-rocm-envs.sh
 COPY scripts/99-toolbox-banner.sh /etc/profile.d/99-toolbox-banner.sh
 COPY scripts/zz-venv-last.sh /etc/profile.d/zz-venv-last.sh