Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 

triton

CONTAINERS IMAGES RUN BUILD

CONTAINERS
triton:3.5.0
   Requires L4T ['>=35']
   Dependencies build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch
   Dockerfile Dockerfile
   Notes The OpenAI triton (https://github.com/triton-lang/triton) wheel that's built is saved in the container under /opt. Based on https://cloud.tencent.com/developer/article/2317398, https://zhuanlan.zhihu.com/p/681714973, https://zhuanlan.zhihu.com/p/673525339
triton:3.4.0
   Aliases triton
   Requires L4T ['>=35']
   Dependencies build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch
   Dependants 4k4d:0.0.0 ai-toolkit apex:0.1 audiocraft awq:0.1.0 bitsandbytes:0.39.1 bitsandbytes:0.45.4 bitsandbytes:0.45.5 bitsandbytes:0.46.0 bitsandbytes:0.47.0 bitsandbytes:0.48.0 block_sparse_attn:0.0.1 cache_dit:0.2.0 causalconv1d:1.6.0 cobra:0.0.1 comfyui cosmos-predict2 cosmos-reason1 cosmos-transfer1 cosmos1-diffusion-renderer:1.0.4 deepspeed:0.15.2 deepspeed:0.18.0 deepspeed:0.9.5 dimba:1.0 dynamo:0.3.2 easyvolcap:0.0.0 exllama:0.1 fast_gauss:1.0.0 flash-attention:2.5.7 flash-attention:2.6.3 flash-attention:2.7.2.post1 flash-attention:2.7.4.post1 flash-attention:2.8.0.post2 flash-attention:2.8.1 flashinfer:0.2.1.post2 flashinfer:0.2.2 flashinfer:0.2.2.post1 flashinfer:0.2.6.post1 flashinfer:0.2.7 flashinfer:0.2.8 flexprefill:0.1.0 framepack fruitnerf:1.0 genai-bench:0.1.0 huggingface_kernels:0.7.0 hymba isaac-gr00t kat:1 l4t-diffusion l4t-dynamo l4t-ml l4t-text-generation lita llama-factory llama-vision llava lobechat local_llm log-linear-attention:0.0.1 mamba:2.2.5 mambavision:1.0 minference:0.1.7 mlc:0.1.0 mlc:0.1.1 mlc:0.1.2 mlc:0.1.3 mlc:0.1.4 mlc:0.19.0 mlc:0.20.0 mlc:0.21.0 mlstm_kernels:2.0.1 mooncake:0.3.5 nano_llm:24.4 nano_llm:24.4-foxy nano_llm:24.4-galactic nano_llm:24.4-humble nano_llm:24.4-iron nano_llm:24.4.1 nano_llm:24.4.1-foxy nano_llm:24.4.1-galactic nano_llm:24.4.1-humble nano_llm:24.4.1-iron nano_llm:24.5 nano_llm:24.5-foxy nano_llm:24.5-galactic nano_llm:24.5-humble nano_llm:24.5-iron nano_llm:24.5.1 nano_llm:24.5.1-foxy nano_llm:24.5.1-galactic nano_llm:24.5.1-humble nano_llm:24.5.1-iron nano_llm:24.6 nano_llm:24.6-foxy nano_llm:24.6-galactic nano_llm:24.6-humble nano_llm:24.6-iron nano_llm:24.7 nano_llm:24.7-foxy nano_llm:24.7-galactic nano_llm:24.7-humble nano_llm:24.7-iron nano_llm:main nano_llm:main-foxy nano_llm:main-galactic nano_llm:main-humble nano_llm:main-iron nerfstudio:1.1.7 nixl:0.3.2 nvidia_modelopt:0.32.0 open3d:1.19.0 openvla openvla:mimicgen paraattention:0.4.0 partpacker:0.1.0 plstm:0.1.0 prismatic pykan:0.2.9 pytorch:2.1-all pytorch:2.2-all pytorch:2.3-all pytorch:2.3.1-all pytorch:2.4-all pytorch:2.5-all pytorch:2.6-all pytorch:2.7-all pytorch:2.8-all radial-attention:0.1.0 robopoint sage-attention:3.0.0 sdnext self-forcing sgl-kernel:0.2.3 sglang:0.4.4 sglang:0.4.6 sglang:0.4.9 sparc3d:0.1.0 sparge-attention:0.1.0 stable-diffusion-webui sudonim:hf tensorrt_llm:0.12 tensorrt_llm:0.22.0 text-generation-inference text-generation-webui:1.7 text-generation-webui:6a7cd01 text-generation-webui:main torch-memory-saver:0.0.7 torchao:0.12.0 torchao:0.13.0 transformer-engine:2.7 videollama:1.0.0 videomambasuite:1.0 vila vllm:0.7.4 vllm:0.8.4 vllm:0.9.0 vllm:0.9.2 vllm:0.9.3 vllm:v0.8.5.post1 voice-pro voicecraft vscode:torch vscode:transformers xattention:0.0.1 xformers:0.0.32 xformers:0.0.33 xlstm:2.0.5 xtuner zigma:1.0
   Dockerfile Dockerfile
   Notes The OpenAI triton (https://github.com/triton-lang/triton) wheel that's built is saved in the container under /opt. Based on https://cloud.tencent.com/developer/article/2317398, https://zhuanlan.zhihu.com/p/681714973, https://zhuanlan.zhihu.com/p/673525339
triton:3.3.1
   Requires L4T ['>=35']
   Dependencies build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch
   Dockerfile Dockerfile
   Notes The OpenAI triton (https://github.com/triton-lang/triton) wheel that's built is saved in the container under /opt. Based on https://cloud.tencent.com/developer/article/2317398, https://zhuanlan.zhihu.com/p/681714973, https://zhuanlan.zhihu.com/p/673525339
triton:3.3.0
   Requires L4T ['>=35']
   Dependencies build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch
   Dockerfile Dockerfile
   Notes The OpenAI triton (https://github.com/triton-lang/triton) wheel that's built is saved in the container under /opt. Based on https://cloud.tencent.com/developer/article/2317398, https://zhuanlan.zhihu.com/p/681714973, https://zhuanlan.zhihu.com/p/673525339
triton:3.2.0
   Requires L4T ['>=35']
   Dependencies build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch
   Dockerfile Dockerfile
   Notes The OpenAI triton (https://github.com/triton-lang/triton) wheel that's built is saved in the container under /opt. Based on https://cloud.tencent.com/developer/article/2317398, https://zhuanlan.zhihu.com/p/681714973, https://zhuanlan.zhihu.com/p/673525339
triton:3.1.0
   Requires L4T ['>=35']
   Dependencies build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch
   Dockerfile Dockerfile
   Notes The OpenAI triton (https://github.com/triton-lang/triton) wheel that's built is saved in the container under /opt. Based on https://cloud.tencent.com/developer/article/2317398, https://zhuanlan.zhihu.com/p/681714973, https://zhuanlan.zhihu.com/p/673525339
triton:3.0.0
   Requires L4T ['>=35']
   Dependencies build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch
   Dockerfile Dockerfile
   Notes The OpenAI triton (https://github.com/triton-lang/triton) wheel that's built is saved in the container under /opt. Based on https://cloud.tencent.com/developer/article/2317398, https://zhuanlan.zhihu.com/p/681714973, https://zhuanlan.zhihu.com/p/673525339
RUN CONTAINER

To start the container, you can use jetson-containers run and autotag, or manually put together a docker run command:

# automatically pull or build a compatible container image
jetson-containers run $(autotag triton)

# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host triton:36.4.0

jetson-containers run forwards arguments to docker run with some defaults added (like --runtime nvidia, mounts a /data cache, and detects devices)
autotag finds a container image that's compatible with your version of JetPack/L4T - either locally, pulled from a registry, or by building it.

To mount your own directories into the container, use the -v or --volume flags:

jetson-containers run -v /path/on/host:/path/in/container $(autotag triton)

To launch the container running a command, as opposed to an interactive shell:

jetson-containers run $(autotag triton) my_app --abc xyz

You can pass any options to it that you would to docker run, and it'll print out the full command that it constructs before executing it.

BUILD CONTAINER

If you use autotag as shown above, it'll ask to build the container for you if needed. To manually build it, first do the system setup, then run:

jetson-containers build triton

The dependencies from above will be built into the container, and it'll be tested during. Run it with --help for build options.