Aditya Aggarwal

NVIDIA TensorRT LLM provides a high-level Python LLM API, with its PyTorch-native architecture enabling developers to experiment with the runtime or extend functionality. Learn how these latest TensorRT-LLM optimizations boost reasoning inference performance in our recent blog post. 🖇️ https://lnkd.in/gx52zwTA #PyTorch #OpenSourceAI #AI #Inference #Innovation

94

2 Comments

Get faster and smarter MOE inference straight out of the box. 👇Deep dive on scaling expert parallelism with TensorRT-LLM. LLMs with MOE promise higher model capacity without linearly increasing compute costs - but they introduce new challenges -- more conditional computation, dynamic routing, and non-uniform GPU utilization -- solved by TensorRT-LLM. ✨ New in TensorRT-LLM has native support for expert parallelism—designed for fast, efficient inference with MoE models like Mixtral (Mistral AI) and DeepSeek (DeepSeek AI). This gives you: ✅ Dynamic expert routing: Automatically route tokens to the top-k experts with minimal overhead. ✅ Efficient expert scheduling: Balance expert loads across GPUs using smart sharding and token bucketization. ✅ Memory-aware execution: Maximize hardware utilization while respecting memory budgets. ✅ Drop-in support: Use @HuggingFace models with minimal code changes via TensorRT-LLM's #Python API. 🧠 How it works: MoE models activate only a subset of "experts" for each token. This dynamic nature is powerful—but hard to optimize. It’s all done under the hood using custom #CUDA kernels and NCCL-based communication primitives—giving you low latency, high throughput, and better GPU scaling. ✨ TensorRT-LLM handles: ✅Token-expert mapping using the gating network. ✅Token sorting to batch same-expert tokens together. ✅Expert parallel execution across GPUs. ✅Merging outputs for final predictions. 🛠️ Developer workflow - here is the code to get started. # Clone the repo git clone https://lnkd.in/g-GiDX23 # Use included examples to load and run a Mixtral model cd TensorRT-LLM/examples/mixtral From there, the Python API lets you load the model, convert it with TensorRT, and run expert parallel inference—all with a few lines of code. Results? 📈 Performance at scale. Tests show up to 2.3x faster inference throughput compared to standard tensor parallelism when using 8 GPUs and top-2 experts per token. Even better—TensorRT-LLM keeps efficiency high across increasing batch sizes. Want to see it in action or contribute? 👉 Read the full tech blog: https://lnkd.in/g_7YV3vV 👉 Explore the code on GitHub: https://lnkd.in/gNjQ5W2U 👉 Follow updates in the TensorRT-LLM repo: https://lnkd.in/gqSHYQ4u Share your experiences with us.

78

3 Comments

Memory management is one of the biggest challenges AI engineers face today. LLMs are stateless by design, which means every intelligent agent needs a robust memory layer to truly perform in real-world environments. With the introduction of the Redis Agent Memory Server, Redis is tackling this challenge head-on. The open-source solution brings a two-tier memory architecture (working + long-term memory), semantic retrieval, metadata filtering, and asynchronous memory extraction — all built for production scale and speed. It’s a powerful example of how Redis continues to evolve beyond caching into a core infrastructure layer for AI-native applications. If you're building AI agents and thinking about context engineering, persistent memory, and intelligent retrieval, you should explore this! Thank you to Andrew Brookins, Principal Applied AI Engineer, and Raphael De Lio, Developer Advocate at Redis, for sharing this article with us! ➡️ Read the full article on our magazine: https://lnkd.in/db3-fhZT #AI #Redis #AgenticAI #LLMs #DeveloperTools

5

Rachit Jain's walkthrough shows how to profile kernels with PyTorch tools, import traces into NVIDIA Nsight or Intel Advisor, and read the slanted ceilings that separate compute-bound from memory-bound regions.

5

PyTorch 2.9 is now available, introducing key updates to performance, portability, and the developer experience. This release includes a stable libtorch ABI for C++/CUDA extensions, symmetric memory for multi-GPU kernels, expanded wheel support to include ROCm, XPU, and CUDA 13, and enhancements for Intel, Arm, and x86 platforms. With 3,216 commits from 452 contributors, PyTorch 2.9 continues to advance open source AI for developers worldwide. 🔗 Read the full release blog: https://hubs.la/Q03NNKqV0 #PyTorch #OpenSourceAI #AI #Performance

1,875

27 Comments

We just published our first technical research note. "Low-Latency Event-Driven Architecture for Real-Time Options Execution on IBKR" It covers how we eliminated compounding feed lag at SPY market open — from a growing 45-second backlog to stable sub-second bar sealing — through: → Queue-first callback offloading (Python GIL problem) → Per-venue DOM isolation across ARCA, ISLAND, IEX → Event-time binning across 6 independent intervals → Single source of truth for all technical indicators No signals. No alpha. Pure infrastructure. This is the kind of work that happens before a single trade fires — and the kind that determines whether your system survives the opening bell. 📄 Download: https://lnkd.in/g-XJsYwG #AlgoTrading #OptionsTrading #MarketMicrostructure #SystematicTrading #Python #QuantitativeFinance #TradingInfrastructure

1

Compressing LLMs but worried about accuracy? 🎯 EoRA uses eigenspace low-rank approximation to compensate for errors—no retraining needed. A promising direction for scalable, task-adaptive LLMs. New paper from #NVIDIAResearch.

1

The real engineering challenge isn’t squeezing more capability out of LLMs. It’s figuring out how to actually run them safely. When an agent can write and execute code, you’re not dealing with AI-powered software anymore. You’re dealing with autonomous software running inside your infrastructure. Most stacks were not built for that. https://lnkd.in/gEScgXdR

7

A lot of real-world planning problems (scheduling, routing, portfolio selection) boil down to combinatorial optimization, and classical heuristics like simulated annealing often get stuck. This blogpost in collaboration between quantum scientists from Amazon Web Services (AWS), BMW Group, Siemens and Technical University of Munich shares a practical hybrid idea: use correlations from a quantum algorithm (like QAOA) to guide cluster moves in a classical search, and on some graph instances it beats simulated annealing. https://lnkd.in/g8UNgbWZ #QuantumComputing #Optimization #HybridComputing

3