Registry / ai-ml / gsplat

gsplat

JSON →
library1.5.3pypypi✓ verified 80d ago

A Python package for differentiable rasterization of 3D Gaussians, widely used in 3D Gaussian Splatting (3DGS) research and applications. Version 1.5.3 includes support for batched scenes, 2DGS, distorted cameras, and CUDA fused Adam optimizer. Release cadence is approximately monthly.

pip install gsplat
INSTALL
IMPORT
SIG · GSPLAT
G
gsplat
ai-mlpythonv1.5.3
Install
68.0s avg
Import
Disk
4890MB
Pass rate
4/ 10
Env Coverage4 / 10
glibc
3.93.13
musl
3.93.13
Install & Compatibility
Where this runs
tested against v1.5.3 · pip install
no network on importno background threads
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
musl
glibc
py 3.10
✕ build_error
✓ 80.9s
py 3.11
✕ build_error
✓ 72.7s
py 3.12
✕ build_error
✓ 60.3s
py 3.13
✕ build_error
✓ 58.2s
py 3.9
✕ build_error
✕ timeout
4890MB installed
● package 4890MB
Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

DefaultStrategy
from gsplat import DefaultStrategy
import gsplat; gsplat.rasterization(...)
Strategy
from gsplat import Strategy
accumulate
from gsplat import accumulate

Minimal example of rasterization with dummy data. Requires CUDA for performance.

import torch import gsplat device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # dummy data: batch of 3D Gaussians (N, 14) gaussians = torch.randn(100, 14, device=device) viewmat = torch.eye(4, device=device).unsqueeze(0) # (1, 4, 4) fx, fy, cx, cy = 100.0, 100.0, 50.0, 50.0 img_height, img_width = 100, 100 rendered = gsplat.rasterization( means=gaussians[:, :3], quats=gaussians[:, 3:7], scales=torch.exp(gaussians[:, 7:10]), opacities=torch.sigmoid(gaussians[:, 10:11]), colors=torch.sigmoid(gaussians[:, 11:14]), viewmat=viewmat, K=torch.tensor([[fx, 0, cx], [0, fy, cy], [0, 0, 1]], device=device), width=img_width, height=img_height, ) print(rendered.keys())
Debug
Known issues
breakingIn v1.0+, the rasterization function signature changed: now expects individual tensors for means, quats, scales, opacities, colors instead of a single packed tensor.
fix
Update calls to pass separate keyword arguments. See docs for current signature.
affects: >=1.0.0
deprecatedThe 'gsplat.cuda_legacy' module is deprecated and will be removed in a future release.
fix
Use 'gsplat.rasterization' directly instead of 'gsplat.cuda_legacy.rasterization'.
affects: >=1.3.0
gotchagsplat requires a CUDA-capable GPU and PyTorch with CUDA. Running on CPU will trigger a RuntimeError about CUDA not being available.
fix
Ensure you have a GPU and install PyTorch with CUDA support (e.g., 'pip install torch==2.2.0+cu118 -f https://download.pytorch.org/whl/torch_stable.html').
affects: all
Upgrade
Version history
1.5.3latest on PyPI · released Jul 4, 2025
Audit
Dependencies
torchrequiredgsplat depends on PyTorch for tensor operations and CUDA support.
Agent activity
11 hits · last 30 days
node
10
OpenAI (training)
1
Resources
gsplat — pip install gsplat · libregistry