nv-auto-deploy/TensorRT-LLM
Apr 2025 – Apr 2025
1 Month active
Languages Used
C++Python
Technical Skills
C++Deep LearningExecutorFull Stack DevelopmentLoRAModel Optimization
shaharmor98
PROFILE
Shaharmor98
Worked on integrating LoRA and PEFT adaptation into the nv-auto-deploy/TensorRT-LLM repository, enabling adapter-based model experimentation and deployment. Developed an end-to-end LoRA flow that supports execution of LoRA adapters from model loading through inference, updating both C++ bindings and Python configuration to handle LoRA parameters. Enhanced the PyExecutor and TensorRT-LLM components by incorporating PEFT caching and modular architecture changes, allowing for flexible, adapter-ready deployments. Leveraged skills in C++, Python, and deep learning to improve cross-language integration and resource management, ultimately accelerating inference deployment workflows and supporting more efficient experimentation with parameter-efficient fine-tuning techniques in production environments.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
2Total
Bugs
0
Commits
2
Features
1
Lines of code
857
Activity Months1
Your Network
1814 peopleSame Organization
@nvidia.com1814
Work History
April 2025
2 Commits • 1 Features
Apr 1, 2025April 2025: Focused on enabling LoRA/PEFT adaptation across PyExecutor and TensorRT-LLM to accelerate experimentation and deployment of adapter-based models. Delivered end-to-end LoRA flow, enhanced PEFT caching, and updated core components (C++ bindings and Python config) to support LoRA parameters, driving faster time-to-value for inference deployments and greater modeling flexibility.
2 Commits • 1 Features
Apr 1, 2025April 2025: Focused on enabling LoRA/PEFT adaptation across PyExecutor and TensorRT-LLM to accelerate experimentation and deployment of adapter-based models. Delivered end-to-end LoRA flow, enhanced PEFT caching, and updated core components (C++ bindings and Python config) to support LoRA parameters, driving faster time-to-value for inference deployments and greater modeling flexibility.
April 2025
Activity
Loading activity data...
Quality Metrics
Correctness90.0%
Maintainability80.0%
Architecture90.0%
Performance80.0%
AI Usage20.0%
Skills & Technologies
Programming Languages
C++Python
Technical Skills
C++Deep LearningExecutorFull Stack DevelopmentLoRAModel OptimizationPEFTPybindPythonResource ManagementTensorRT
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline