Registry / ai-ml / tensorrt-cu12-libs

tensorrt-cu12-libs

JSON →
library11.1.0.106pypypiunverified

NVIDIA TensorRT libraries for CUDA 12.x, providing core runtime and plugin libraries for high-performance deep learning inference. Current version 10.16.1.11. Released on PyPI as a separate wheel to isolate CUDA 12 dependencies; updates follow TensorRT releases (approximately quarterly).

pip install tensorrt-cu12-libs==10.16.1.11
INSTALL
IMPORT
SIG · TENSORRT-CU12-LIBS
T
tensorrt-cu12-libs
ai-mlpythonv11.1.0.106
Install
78.4s avg
Import
Disk
6349MB
Pass rate
5/ 10
Env Coverage5 / 10
glibc
3.93.13
musl
3.93.13
Install & Compatibility
Where this runs
tested against v10.16.1.11 · 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
py 3.103.95 runs
build_error
glibc
py 3.103.95 runs
installs and imports cleanly · install 78.4s · import 0.000s · 6348.8MB
6349MB installed
● package 6349MB
Code
Verified usage

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

tensorrt
import tensorrt as trt
from tensorrt import *
Importing all with * pollutes namespace; use alias trt.

Verifies TensorRT installation and creates a trivial identity engine.

import tensorrt as trt import os # Verify installation print(f"TensorRT version: {trt.__version__}") # Create a logger logger = trt.Logger(trt.Logger.WARNING) # Build a simple identity network builder = trt.Builder(logger) network = builder.create_network(1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)) # Add an input tensor input_tensor = network.add_input(name="input", dtype=trt.float32, shape=(1, 3, 224, 224)) # Add an identity layer (pass-through) identity = network.add_identity(input_tensor) # Mark output network.mark_output(identity.get_output(0)) # Build engine config = builder.create_builder_config() config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, 1 << 30) # 1 GB engine_bytes = builder.build_serialized_network(network, config) if engine_bytes: print("Engine built successfully") else: print("Engine build failed")
Debug
Known issues
breakingThe tensorrt-cu12-libs package only supports CUDA 12.x. On CUDA 11 systems, use tensorrt-cu11-libs instead. Mixing CUDA versions causes cryptic runtime errors.
fix
Check CUDA version via `nvcc --version` and install matching -cuXX- variant.
affects: >=10.0
breakingAll tensorrt-* packages (libs, bindings, python) must be the same version. Version mismatch leads to import errors or segmentation faults.
fix
Install exact same version for all components, e.g., pip install tensorrt-cu12-libs==10.16.1.11 tensorrt-cu12-bindings==10.16.1.11 tensorrt==10.16.1.11
affects: >=10.0
gotchaThe tensorrt-cu12-libs wheel does not include the Python bindings; you must install tensorrt or tensorrt-cu12-bindings separately.
fix
Also install tensorrt (full) or tensorrt-cu12-bindings (Python bindings only).
affects: >=10.0
deprecatedTensorRT 10.16 defaults to CUDA 13.2; the cu12 variant is available for legacy CUDA 12 compatibility but may be dropped in future releases.
fix
Plan migration to CUDA 13.2 to use the default tensorrt package.
affects: >=10.16
Upgrade
Version history
11.1.0.106latest on PyPI · released Jun 16, 2026
Audit
Dependencies
tensorrt-cu12-bindingsrequiredPython bindings that wrap the libraries; both must match version exactly.
cuda-pythonoptionalRequired for CUDA context management and memory transfers in Python workflows.
Agent activity
47 hits · last 30 days
node
46
OpenAI (training)
1
Resources
homepagenull
tensorrt-cu12-libs — pip install tensorrt-cu12-libs · libregistry