From 135b799b13bb5c8132bbe0753600b5543fb712db Mon Sep 17 00:00:00 2001
From: Shang Chieh Tseng <shangchieh.tseng@tsengsyu.com>
Date: Wed, 29 Oct 2025 14:21:03 +0800
Subject: [PATCH] Update command.

---
 CLAUDE.md            | 32 ++------------------------------
 docs/manual-build.md |  8 ++++----
 2 files changed, 6 insertions(+), 34 deletions(-)

diff --git a/CLAUDE.md b/CLAUDE.md
index 61cdcfe2..36cc1cfb 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -39,22 +39,6 @@ The project documentation is organized as follows:
 
 ### Building the Project
 
-#### Quick Build
-```bash
-# Configure build (required on Linux/Intel macOS/Windows)
-cmake -B build
-cmake --build build
-
-# For ROCm on Windows
-cmake -B build -G Ninja -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++
-cmake --build build --config Release
-
-# Build Go binary
-go build -o ollama .
-```
-
-#### Tesla K80 Optimized Build
-For Tesla K80 and CUDA Compute Capability 3.7 hardware, use specific compiler versions:
 ```bash
 # Configure with GCC 10 and CUDA 11.4 support
 CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -B build
@@ -90,18 +74,6 @@ go test ./integration/...
 go test ./server/...
 ```
 
-### Docker
-```bash
-# Build standard image
-docker build .
-
-# Build with ROCm support
-docker build --build-arg FLAVOR=rocm .
-
-# Build ollama37 image for Tesla K80/Compute 3.7 support
-docker build -f ollama37.Dockerfile -t ollama37 .
-```
-
 ## Architecture Overview
 
 Ollama is a local LLM server with Go backend and C++/CUDA acceleration:
@@ -155,7 +127,7 @@ The project supports multiple acceleration backends:
 
 Libraries are dynamically loaded from:
 - `./lib/ollama` (Windows)
-- `../lib/ollama` (Linux) 
+- `../lib/ollama` (Linux)
 - `.` (macOS)
 - `build/lib/ollama` (development)
 
@@ -170,4 +142,4 @@ Libraries are dynamically loaded from:
 - Unit tests throughout codebase (`*_test.go`)
 - Integration tests in `integration/` requiring running server
 - Benchmark tests for performance validation
-- Platform-specific test files for GPU/hardware features
\ No newline at end of file
+- Platform-specific test files for GPU/hardware features
diff --git a/docs/manual-build.md b/docs/manual-build.md
index ba1af1f1..44fb81b5 100644
--- a/docs/manual-build.md
+++ b/docs/manual-build.md
@@ -37,8 +37,8 @@ git clone https://github.com/dogkeeper886/ollama37
 cd ollama37
 
 # If compiling from source (requires GCC 10):
-cmake -B build
-cmake --build build -j$(nproc)
+CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -B build
+CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake --build build -j$(nproc)
 go build -o ollama .
 
 # If using pre-built binary (GCC 10 not required):
@@ -522,13 +522,13 @@ go version
 3. **CMake Configuration:**
    Set compiler variables and configure the build system:
    ```bash
-   cmake -B build
+   CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -B build
    ```
 
 4. **CMake Build:**
    Compile the C++ components (parallel build):
    ```bash
-   cmake --build build -j$(nproc)
+   CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake --build build -j$(nproc)
    ```
 
    > **Note:** `-j$(nproc)` enables parallel compilation using all available CPU cores. You can specify a number like `-j4` to limit the number of parallel jobs.