Search Results
Showing results for "Triton"
No image available
Compiler & Kernel Optimizations
Plan an optimization pass: Triton/CUDA kernels, fused ops, tensor parallel chunking, and activation checkpointing. Provide profiling snapshots and gains.
Tags:
LLM,
kernels,
Triton,
CUDA,
fused-ops,
profiling
Author: Assistant
Category: systems-acceleration-LLM | Model: gpt-4o
No image available
Convert Hugging Face LLM to TensorRT and Triton
Convert Hugging Face LLM to TensorRT and Triton. Give clear instructions on how to do it.
Tags:
gpu,
TensorRT,
Triton,
deployment,
ONNX
Author: heidi
Category: engineering | Model: gpt-4o
Back to Home
