diff --git a/README.md b/README.md
index 7486aef4d..583c858bd 100644
--- a/README.md
+++ b/README.md
@@ -44,15 +44,15 @@ FastVideo has the following features:
 
 ## Getting Started
 
-We recommend using an environment manager such as `Conda` to create a clean environment:
+We recommend using [uv](https://docs.astral.sh/uv/) to create a clean environment. If you previously used Conda, switching to uv generally gives faster and more stable installs.
 
 ```bash
-# Create and activate a new conda environment
-conda create -n fastvideo python=3.12
-conda activate fastvideo
+# Create and activate a new uv environment
+uv venv --python 3.12 --seed
+source .venv/bin/activate
 
 # Install FastVideo
-pip install fastvideo
+uv pip install fastvideo
 ```
 
 Please see our [docs](https://hao-ai-lab.github.io/FastVideo/getting_started/installation/) for more detailed installation instructions.
diff --git a/docs/contributing/overview.md b/docs/contributing/overview.md
index 94f42632c..1524b4fd3 100644
--- a/docs/contributing/overview.md
+++ b/docs/contributing/overview.md
@@ -14,24 +14,11 @@ improving performance, or fixing a bug.
 
 For a full install checklist, see `docs/getting_started/installation/gpu.md`.
 
-## Local development (Conda + editable install)
+## Local development (UV + editable install)
 
-Install Miniconda:
+If you previously used Conda for local setup, switch to uv for a faster and more stable development environment.
 
-```bash
-wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
-bash Miniconda3-latest-Linux-x86_64.sh
-source ~/.bashrc
-```
-
-Create and activate a Conda environment:
-
-```bash
-conda create -n fastvideo python=3.12 -y
-conda activate fastvideo
-```
-
-Install `uv` (optional, but recommended):
+Install `uv`:
 
 ```bash
 curl -LsSf https://astral.sh/uv/install.sh | sh
@@ -39,6 +26,20 @@ curl -LsSf https://astral.sh/uv/install.sh | sh
 wget -qO- https://astral.sh/uv/install.sh | sh
 ```
 
+Create and activate a uv environment (recommended):
+
+```bash
+uv venv --python 3.12 --seed
+source .venv/bin/activate
+```
+
+Conda alternative (supported):
+
+```bash
+conda create -n fastvideo python=3.12 -y
+conda activate fastvideo
+```
+
 Clone the repo:
 
 ```bash
@@ -51,7 +52,7 @@ Install FastVideo in editable mode and set up hooks:
 uv pip install -e .[dev]
 
 # Optional: FlashAttention (builds native kernels)
-uv pip install flash-attn --no-build-isolation
+uv pip install flash-attn --no-build-isolation -v
 
 # Linting, formatting, static typing
 pre-commit install --hook-type pre-commit --hook-type commit-msg
diff --git a/docs/getting_started/installation.md b/docs/getting_started/installation.md
index ebbaeeee1..688ea61d6 100644
--- a/docs/getting_started/installation.md
+++ b/docs/getting_started/installation.md
@@ -8,17 +8,9 @@ FastVideo supports the following hardware platforms:
 
 ## Quick Installation
 
-### Using pip
+### Using uv (recommended)
 
-```bash
-# Create and activate a new conda environment
-conda create -n fastvideo python=3.12
-conda activate fastvideo
-
-pip install fastvideo
-```
-
-### Using uv
+Use uv as the default environment manager for faster and more stable installs.
 
 ```bash
 # Create and activate a new uv environment
@@ -28,21 +20,32 @@ source .venv/bin/activate
 uv pip install fastvideo
 ```
 
+### Using Conda (alternative)
+
+```bash
+# Create and activate a new conda environment
+conda create -n fastvideo python=3.12 -y
+conda activate fastvideo
+
+pip install fastvideo
+```
+
 ### From source
 
 ```bash
 git clone https://github.com/hao-ai-lab/FastVideo.git
 cd FastVideo
-pip install -e .
-
-# or if you are using uv
 uv pip install -e .
+
+# optional: install flash-attn
+uv pip install flash-attn --no-build-isolation -v
 ```
 
-Also optionally install flash-attn:
+Alternative with Conda environment:
 
 ```bash
-pip install flash-attn --no-build-isolation
+pip install -e .
+pip install flash-attn --no-build-isolation -v
 ```
 
 ## Hardware Requirements
diff --git a/docs/getting_started/installation/gpu.md b/docs/getting_started/installation/gpu.md
index a96e310ff..aac55a704 100644
--- a/docs/getting_started/installation/gpu.md
+++ b/docs/getting_started/installation/gpu.md
@@ -12,8 +12,20 @@ Instructions to install FastVideo for NVIDIA CUDA GPUs.
 ## Set up using Python
 ### Create a new Python environment
 
-#### Conda
-You can create a new python environment using [Conda](https://docs.conda.io/projects/conda/en/stable/user-guide/getting-started.html)
+#### uv
+Recommended default: use [uv](https://docs.astral.sh/uv/) for faster and more stable environment setup.
+
+Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, create a new environment using:
+
+```console
+# (Recommended) Create a new uv environment. Use `--seed` to install `pip` and `setuptools`.
+uv venv --python 3.12 --seed
+source .venv/bin/activate
+```
+
+#### Conda (alternative)
+You can also create a Python environment using [Conda](https://docs.conda.io/projects/conda/en/stable/user-guide/getting-started.html).
+
 ##### 1. Install Miniconda (if not already installed)
 
 ```bash
@@ -25,34 +37,35 @@ source ~/.bashrc
 ##### 2. Create and activate a Conda environment for FastVideo
 
 ```bash
-# (Recommended) Create a new conda environment.
+# Create and activate a Conda environment
 conda create -n fastvideo python=3.12 -y
 conda activate fastvideo
 ```
 
-#### uv
-
-Or you can create a new Python environment using [uv](https://docs.astral.sh/uv/), a very fast Python environment manager. Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, you can create a new Python environment using the following command:
-
-```console
-# (Recommended) Create a new uv environment. Use `--seed` to install `pip` and `setuptools` in the environment.
-uv venv --python 3.12 --seed
-source .venv/bin/activate
-```
-
 ### Installation
 
-```bash
-pip install fastvideo
+#### With uv (recommended)
 
-# or if you are using uv
+```bash
 uv pip install fastvideo
 ```
 
-Also optionally install flash-attn:
+Also optionally install FlashAttention:
 
 ```bash
-pip install flash-attn --no-build-isolation
+uv pip install flash-attn --no-build-isolation -v
+```
+
+#### With Conda environment (alternative)
+
+```bash
+pip install fastvideo
+```
+
+Also optionally install FlashAttention:
+
+```bash
+pip install flash-attn --no-build-isolation -v
 ```
 
 ### Installation from Source
@@ -68,18 +81,27 @@ git clone https://github.com/hao-ai-lab/FastVideo.git && cd FastVideo
 Basic installation:
 
 ```bash
-pip install -e .
-
-# or if you are using uv
 uv pip install -e .
 ```
 
+Alternative with Conda environment:
+
+```bash
+pip install -e .
+```
+
 ### Optional Dependencies
 
 #### Flash Attention
 
 ```bash
-pip install flash-attn --no-build-isolation
+uv pip install flash-attn --no-build-isolation -v
+```
+
+Alternative with Conda environment:
+
+```bash
+pip install flash-attn --no-build-isolation -v
 ```
 
 ## Set up using Docker
diff --git a/docs/getting_started/installation/mps.md b/docs/getting_started/installation/mps.md
index 6265d1246..18b816f8f 100644
--- a/docs/getting_started/installation/mps.md
+++ b/docs/getting_started/installation/mps.md
@@ -11,9 +11,20 @@ Instructions to install FastVideo for Apple Silicon.
 
 ### Create a new Python environment
 
-#### Conda
+#### uv
+Recommended default: use [uv](https://docs.astral.sh/uv/) for faster and more stable environment setup.
 
-You can create a new python environment using [Conda](https://docs.conda.io/projects/conda/en/stable/user-guide/getting-started.html)
+Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, create a new environment using:
+
+```console
+# (Recommended) Create a new uv environment. Use `--seed` to install `pip` and `setuptools`.
+uv venv --python 3.12 --seed
+source .venv/bin/activate
+```
+
+#### Conda (alternative)
+
+You can also create a Python environment using [Conda](https://docs.conda.io/projects/conda/en/stable/user-guide/getting-started.html).
 
 ##### 1. Install Miniconda (if not already installed)
 
@@ -26,21 +37,10 @@ source ~/.zshrc
 ##### 2. Create and activate a Conda environment for FastVideo
 
 ```bash
-# (Recommended) Create a new conda environment.
 conda create -n fastvideo python=3.12.4 -y
 conda activate fastvideo
 ```
 
-#### uv
-
-Or you can create a new Python environment using [uv](https://docs.astral.sh/uv/), a very fast Python environment manager. Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, you can create a new Python environment using the following command:
-
-```console
-# (Recommended) Create a new uv environment. Use `--seed` to install `pip` and `setuptools` in the environment.
-uv venv --python 3.12 --seed
-source .venv/bin/activate
-```
-
 ### Dependencies
 
 ```
@@ -49,11 +49,16 @@ brew install ffmpeg
 
 ### Installation
 
+#### With uv (recommended)
+
+```bash
+uv pip install fastvideo
+```
+
+#### With Conda environment (alternative)
+
 ```bash
 pip install fastvideo
-
-# or if you are using uv
-uv pip install fastvideo
 ```
 
 ### Installation from Source
@@ -69,12 +74,15 @@ git clone https://github.com/hao-ai-lab/FastVideo.git && cd FastVideo
 Basic installation:
 
 ```bash
-pip install -e .
-
-# or if you are using uv
 uv pip install -e .
 ```
 
+Alternative with Conda environment:
+
+```bash
+pip install -e .
+```
+
 ## Development Environment Setup
 
 If you're planning to contribute to FastVideo please see the following page:
diff --git a/docs/getting_started/quick_start.md b/docs/getting_started/quick_start.md
index 7779a5279..59dbe75d0 100644
--- a/docs/getting_started/quick_start.md
+++ b/docs/getting_started/quick_start.md
@@ -7,18 +7,18 @@ Get up and running with FastVideo in minutes!
 First, install FastVideo:
 
 ```bash
-# Create and activate a new conda environment
-conda create -n fastvideo python=3.12
-conda activate fastvideo
+# If you previously used Conda, use uv instead for a faster, more stable setup
+uv venv --python 3.12 --seed
+source .venv/bin/activate
 
 # Install FastVideo
-pip install fastvideo
+uv pip install fastvideo
 ```
 
 Also optionally install flash-attn:
 
 ```bash
-pip install flash-attn --no-build-isolation
+uv pip install flash-attn --no-build-isolation -v
 ```
 
 ## Basic Usage
diff --git a/docs/inference/inference_quick_start.md b/docs/inference/inference_quick_start.md
index b3305b728..6d5d10791 100644
--- a/docs/inference/inference_quick_start.md
+++ b/docs/inference/inference_quick_start.md
@@ -11,15 +11,15 @@ This page contains step-by-step instructions to get you quickly started with vid
 
 ## Installation
 
-We recommend using an environment manager such as `Conda` to create a clean environment:
+If you previously used Conda, we recommend using [uv](https://docs.astral.sh/uv/) instead for a faster and more stable environment setup:
 
 ```bash
-# Create and activate a new conda environment
-conda create -n fastvideo python=3.12
-conda activate fastvideo
+# Create and activate a new uv environment
+uv venv --python 3.12 --seed
+source .venv/bin/activate
 
 # Install FastVideo
-pip install fastvideo
+uv pip install fastvideo
 ```
 
 For advanced installation options, see the [Installation Guide](../getting_started/installation.md).
diff --git a/fastvideo-kernel/README.md b/fastvideo-kernel/README.md
index 010779280..82d3fe81d 100644
--- a/fastvideo-kernel/README.md
+++ b/fastvideo-kernel/README.md
@@ -7,6 +7,13 @@ CUDA kernels for FastVideo video generation.
 ### Standard Installation (Local Development)
 This will automatically detect your GPU architecture. If an NVIDIA Hopper (H100/sm_90a) GPU is detected, ThunderKittens kernels will be enabled. Otherwise, they will be skipped, and the package will use Triton fallbacks at runtime.
 
+Before installation, set CUDA toolchain paths:
+
+```bash
+export CUDA_HOME=/usr/local/cuda
+export CUDACXX=$CUDA_HOME/bin/nvcc
+```
+
 ```bash
 git submodule update --init --recursive
 cd fastvideo-kernel
@@ -62,6 +69,8 @@ This package also includes kernels from [TurboDiffusion](https://github.com/thu-
   - Any CUDA GPU for Triton-based fallbacks.
 - **Build**:
   - CUDA Toolkit 12.3+
+  - `CUDA_HOME` must be set (for example, `/usr/local/cuda`)
+  - `CUDACXX` must be set (for example, `$CUDA_HOME/bin/nvcc`)
   - C++20 compatible compiler (GCC 10+, Clang 11+)
 
 ## Acknowledgement
diff --git a/fastvideo-kernel/build.sh b/fastvideo-kernel/build.sh
index 9437a87d3..107952375 100755
--- a/fastvideo-kernel/build.sh
+++ b/fastvideo-kernel/build.sh
@@ -3,8 +3,10 @@ set -ex
 
 # Simple build script wrapping uv/pip
 # Usage:
-#   ./build.sh                # local dev build (auto-detect / skip TK kernels when not available)
-#   ./build.sh --release      # force-enable Hopper/TK kernels for release builds (no GPU required)
+#   ./build.sh  # local build (torch-based arch detection, TK only on SM90)
+# Environment overrides (if set, they win over auto-detection):
+#   TORCH_CUDA_ARCH_LIST
+#   CMAKE_ARGS (for FASTVIDEO_KERNEL_BUILD_TK / CMAKE_CUDA_ARCHITECTURES / GPU_BACKEND)
 
 echo "Building fastvideo-kernel..."
 
@@ -12,7 +14,7 @@ echo "Building fastvideo-kernel..."
 git submodule update --init --recursive
 
 # Install build dependencies
-pip install scikit-build-core cmake ninja
+uv pip install scikit-build-core cmake ninja
 
 RELEASE=0
 GPU_BACKEND=CUDA
@@ -24,15 +26,68 @@ for arg in "$@"; do
     esac
 done
 
-# Force-enable ThunderKittens kernels and compile for Hopper.
-export TORCH_CUDA_ARCH_LIST="9.0a"
-export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
+has_cmake_arg() {
+    local key="$1"
+    [[ "${CMAKE_ARGS:-}" =~ (^|[[:space:]])-D${key}(=|$) ]]
+}
 
-export CMAKE_ARGS="${CMAKE_ARGS:-} -DGPU_BACKEND=${GPU_BACKEND}"
+detect_with_torch() {
+    uv run --active --no-project python -c "import torch
+if not torch.cuda.is_available():
+    raise RuntimeError('torch.cuda.is_available() is false')
+mj, mn = torch.cuda.get_device_capability(0)
+print(f'{mj}.{mn}')"
+}
+
+if [ "${GPU_BACKEND}" = "CUDA" ]; then
+    detected_cc="$(detect_with_torch)" || {
+        echo "ERROR: torch-based CUDA arch detection failed in uv environment." >&2
+        echo "       Ensure torch is installed and CUDA is available in the uv-selected Python." >&2
+        exit 1
+    }
+
+    cc_major="${detected_cc%%.*}"
+    cc_minor="${detected_cc##*.}"
+    cmake_arch="${cc_major}${cc_minor}"
+    echo "Detected compute capability via torch: ${detected_cc} (sm_${cmake_arch})"
+
+    # Respect explicit overrides.
+    if [ -z "${TORCH_CUDA_ARCH_LIST:-}" ]; then
+        if [ "${cc_major}" = "9" ] && [ "${cc_minor}" = "0" ]; then
+            export TORCH_CUDA_ARCH_LIST="9.0a"
+        else
+            export TORCH_CUDA_ARCH_LIST="${cc_major}.${cc_minor}"
+        fi
+    fi
+
+    # ThunderKittens build targeting:
+    # - SM90: compile Hopper/TK kernels with 90a.
+    # - Others (e.g., SM100): compile non-TK path with detected arch.
+    if ! has_cmake_arg "CMAKE_CUDA_ARCHITECTURES"; then
+        if [ "${cc_major}" = "9" ] && [ "${cc_minor}" = "0" ]; then
+            CMAKE_ARGS="${CMAKE_ARGS:-} -DCMAKE_CUDA_ARCHITECTURES=90a"
+        else
+            CMAKE_ARGS="${CMAKE_ARGS:-} -DCMAKE_CUDA_ARCHITECTURES=${cmake_arch}"
+        fi
+    fi
+
+    if ! has_cmake_arg "FASTVIDEO_KERNEL_BUILD_TK"; then
+        if [ "${cc_major}" = "9" ] && [ "${cc_minor}" = "0" ]; then
+            CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON"
+        else
+            CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=OFF"
+        fi
+    fi
+fi
+
+if ! has_cmake_arg "GPU_BACKEND"; then
+    CMAKE_ARGS="${CMAKE_ARGS:-} -DGPU_BACKEND=${GPU_BACKEND}"
+fi
+export CMAKE_ARGS
 
 echo "TORCH_CUDA_ARCH_LIST: ${TORCH_CUDA_ARCH_LIST:-<unset>}"
 echo "CMAKE_ARGS: ${CMAKE_ARGS:-<unset>}"
 echo "GPU_BACKEND: ${GPU_BACKEND:-<unset>}"
 # Build and install
 # Use -v for verbose output
-pip install . -v --no-build-isolation
+uv pip install . -v --no-build-isolation