warpgbm 0.1.13__tar.gz → 0.1.14__tar.gz

{warpgbm-0.1.13/warpgbm.egg-info → warpgbm-0.1.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warpgbm
-Version: 0.1.13
+Version: 0.1.14
 Summary: A fast GPU-accelerated Gradient Boosted Decision Tree library with PyTorch + CUDA
 License:                     GNU GENERAL PUBLIC LICENSE
                                Version 3, 29 June 2007
@@ -700,7 +700,6 @@ WarpGBM is a high-performance, GPU-accelerated Gradient Boosted Decision Tree (G
 - GPU-accelerated training and histogram construction using custom CUDA kernels
 - Drop-in scikit-learn style interface
 - Supports pre-binned data or automatic quantile binning
-- Fully differentiable prediction path
 - Simple install with `pip`
 
 ---
@@ -713,7 +712,7 @@ In our initial tests on an NVIDIA 3090 (local) and A100 (Google Colab Pro), Warp
 
 ## Installation
 
-### 🔧 Recommended (GitHub, always latest):
+### Recommended (GitHub, always latest):
 
 ```bash
 pip install git+https://github.com/jefferythewind/warpgbm.git
@@ -721,7 +720,7 @@ pip install git+https://github.com/jefferythewind/warpgbm.git
 
 This installs the latest version directly from GitHub and compiles CUDA extensions on your machine using your **local PyTorch and CUDA setup**. It's the most reliable method for ensuring compatibility and staying up to date with the latest features.
 
-### 📦 Alternatively (PyPI, stable releases):
+### Alternatively (PyPI, stable releases):
 
 ```bash
 pip install warpgbm
@@ -729,7 +728,7 @@ pip install warpgbm
 
 This installs from PyPI and also compiles CUDA code locally during installation. This method works well **if your environment already has PyTorch with GPU support** installed and configured.
 
-> 💡 **Tip:**\
+> **Tip:**\
 > If you encounter an error related to mismatched or missing CUDA versions, try installing with the following flag:
 >
 > ```bash
@@ -737,7 +736,7 @@ This installs from PyPI and also compiles CUDA code locally during installation.
 > ```
 
 Before either method, make sure you’ve installed PyTorch with GPU support:\
-👉 [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
+[https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
 
 ---
 
@@ -774,7 +773,7 @@ print(f"LightGBM:   corr = {np.corrcoef(lgb_preds, y)[0,1]:.4f}, time = {lgb_tim
 print(f"WarpGBM:     corr = {np.corrcoef(wgbm_preds, y)[0,1]:.4f}, time = {wgbm_time:.2f}s")
 ```
 
-**🧪 Results (Ryzen 9 CPU, NVIDIA 3090 GPU):**
+**Results (Ryzen 9 CPU, NVIDIA 3090 GPU):**
 
 ```
 LightGBM:   corr = 0.8742, time = 37.33s
@@ -824,6 +823,23 @@ print(f"LightGBM:   corr = {np.corrcoef(lgb_preds, Y_np)[0,1]:.4f}, time = {lgb_
 print(f"WarpGBM:     corr = {np.corrcoef(wgbm_preds, Y_np)[0,1]:.4f}, time = {wgbm_time:.2f}s")
 ```
 
+**Results (Google Colab Pro, A100 GPU):**
+
+```
+LightGBM:   corr = 0.0703, time = 643.88s
+WarpGBM:     corr = 0.0660, time = 49.16s
+```
+
+---
+
+### Run it live in Colab
+
+You can try WarpGBM in a live Colab notebook using real pre-binned Numerai tournament data:
+
+[Open in Colab](https://colab.research.google.com/drive/10mKSjs9UvmMgM5_lOXAylq5LUQAnNSi7?usp=sharing)
+
+No installation required — just press **"Open in Playground"**, then **Run All**!
+
 ---
 
 ## Documentation

{warpgbm-0.1.13 → warpgbm-0.1.14}/README.md

@@ -12,7 +12,6 @@ WarpGBM is a high-performance, GPU-accelerated Gradient Boosted Decision Tree (G
 - GPU-accelerated training and histogram construction using custom CUDA kernels
 - Drop-in scikit-learn style interface
 - Supports pre-binned data or automatic quantile binning
-- Fully differentiable prediction path
 - Simple install with `pip`
 
 ---
@@ -25,7 +24,7 @@ In our initial tests on an NVIDIA 3090 (local) and A100 (Google Colab Pro), Warp
 
 ## Installation
 
-### 🔧 Recommended (GitHub, always latest):
+### Recommended (GitHub, always latest):
 
 ```bash
 pip install git+https://github.com/jefferythewind/warpgbm.git
@@ -33,7 +32,7 @@ pip install git+https://github.com/jefferythewind/warpgbm.git
 
 This installs the latest version directly from GitHub and compiles CUDA extensions on your machine using your **local PyTorch and CUDA setup**. It's the most reliable method for ensuring compatibility and staying up to date with the latest features.
 
-### 📦 Alternatively (PyPI, stable releases):
+### Alternatively (PyPI, stable releases):
 
 ```bash
 pip install warpgbm
@@ -41,7 +40,7 @@ pip install warpgbm
 
 This installs from PyPI and also compiles CUDA code locally during installation. This method works well **if your environment already has PyTorch with GPU support** installed and configured.
 
-> 💡 **Tip:**\
+> **Tip:**\
 > If you encounter an error related to mismatched or missing CUDA versions, try installing with the following flag:
 >
 > ```bash
@@ -49,7 +48,7 @@ This installs from PyPI and also compiles CUDA code locally during installation.
 > ```
 
 Before either method, make sure you’ve installed PyTorch with GPU support:\
-👉 [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
+[https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
 
 ---
 
@@ -86,7 +85,7 @@ print(f"LightGBM:   corr = {np.corrcoef(lgb_preds, y)[0,1]:.4f}, time = {lgb_tim
 print(f"WarpGBM:     corr = {np.corrcoef(wgbm_preds, y)[0,1]:.4f}, time = {wgbm_time:.2f}s")
 ```
 
-**🧪 Results (Ryzen 9 CPU, NVIDIA 3090 GPU):**
+**Results (Ryzen 9 CPU, NVIDIA 3090 GPU):**
 
 ```
 LightGBM:   corr = 0.8742, time = 37.33s
@@ -136,6 +135,23 @@ print(f"LightGBM:   corr = {np.corrcoef(lgb_preds, Y_np)[0,1]:.4f}, time = {lgb_
 print(f"WarpGBM:     corr = {np.corrcoef(wgbm_preds, Y_np)[0,1]:.4f}, time = {wgbm_time:.2f}s")
 ```
 
+**Results (Google Colab Pro, A100 GPU):**
+
+```
+LightGBM:   corr = 0.0703, time = 643.88s
+WarpGBM:     corr = 0.0660, time = 49.16s
+```
+
+---
+
+### Run it live in Colab
+
+You can try WarpGBM in a live Colab notebook using real pre-binned Numerai tournament data:
+
+[Open in Colab](https://colab.research.google.com/drive/10mKSjs9UvmMgM5_lOXAylq5LUQAnNSi7?usp=sharing)
+
+No installation required — just press **"Open in Playground"**, then **Run All**!
+
 ---
 
 ## Documentation

{warpgbm-0.1.13 → warpgbm-0.1.14}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "warpgbm"
-version = "0.1.13"
+version = "0.1.14"
 description = "A fast GPU-accelerated Gradient Boosted Decision Tree library with PyTorch + CUDA"
 readme = "README.md"
 requires-python = ">=3.8"

warpgbm-0.1.14/version.txt

@@ -0,0 +1 @@
+0.1.14

{warpgbm-0.1.13 → warpgbm-0.1.14/warpgbm.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warpgbm
-Version: 0.1.13
+Version: 0.1.14
 Summary: A fast GPU-accelerated Gradient Boosted Decision Tree library with PyTorch + CUDA
 License:                     GNU GENERAL PUBLIC LICENSE
                                Version 3, 29 June 2007
@@ -700,7 +700,6 @@ WarpGBM is a high-performance, GPU-accelerated Gradient Boosted Decision Tree (G
 - GPU-accelerated training and histogram construction using custom CUDA kernels
 - Drop-in scikit-learn style interface
 - Supports pre-binned data or automatic quantile binning
-- Fully differentiable prediction path
 - Simple install with `pip`
 
 ---
@@ -713,7 +712,7 @@ In our initial tests on an NVIDIA 3090 (local) and A100 (Google Colab Pro), Warp
 
 ## Installation
 
-### 🔧 Recommended (GitHub, always latest):
+### Recommended (GitHub, always latest):
 
 ```bash
 pip install git+https://github.com/jefferythewind/warpgbm.git
@@ -721,7 +720,7 @@ pip install git+https://github.com/jefferythewind/warpgbm.git
 
 This installs the latest version directly from GitHub and compiles CUDA extensions on your machine using your **local PyTorch and CUDA setup**. It's the most reliable method for ensuring compatibility and staying up to date with the latest features.
 
-### 📦 Alternatively (PyPI, stable releases):
+### Alternatively (PyPI, stable releases):
 
 ```bash
 pip install warpgbm
@@ -729,7 +728,7 @@ pip install warpgbm
 
 This installs from PyPI and also compiles CUDA code locally during installation. This method works well **if your environment already has PyTorch with GPU support** installed and configured.
 
-> 💡 **Tip:**\
+> **Tip:**\
 > If you encounter an error related to mismatched or missing CUDA versions, try installing with the following flag:
 >
 > ```bash
@@ -737,7 +736,7 @@ This installs from PyPI and also compiles CUDA code locally during installation.
 > ```
 
 Before either method, make sure you’ve installed PyTorch with GPU support:\
-👉 [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
+[https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
 
 ---
 
@@ -774,7 +773,7 @@ print(f"LightGBM:   corr = {np.corrcoef(lgb_preds, y)[0,1]:.4f}, time = {lgb_tim
 print(f"WarpGBM:     corr = {np.corrcoef(wgbm_preds, y)[0,1]:.4f}, time = {wgbm_time:.2f}s")
 ```
 
-**🧪 Results (Ryzen 9 CPU, NVIDIA 3090 GPU):**
+**Results (Ryzen 9 CPU, NVIDIA 3090 GPU):**
 
 ```
 LightGBM:   corr = 0.8742, time = 37.33s
@@ -824,6 +823,23 @@ print(f"LightGBM:   corr = {np.corrcoef(lgb_preds, Y_np)[0,1]:.4f}, time = {lgb_
 print(f"WarpGBM:     corr = {np.corrcoef(wgbm_preds, Y_np)[0,1]:.4f}, time = {wgbm_time:.2f}s")
 ```
 
+**Results (Google Colab Pro, A100 GPU):**
+
+```
+LightGBM:   corr = 0.0703, time = 643.88s
+WarpGBM:     corr = 0.0660, time = 49.16s
+```
+
+---
+
+### Run it live in Colab
+
+You can try WarpGBM in a live Colab notebook using real pre-binned Numerai tournament data:
+
+[Open in Colab](https://colab.research.google.com/drive/10mKSjs9UvmMgM5_lOXAylq5LUQAnNSi7?usp=sharing)
+
+No installation required — just press **"Open in Playground"**, then **Run All**!
+
 ---
 
 ## Documentation

warpgbm-0.1.13/version.txt

@@ -1 +0,0 @@
-0.1.13