Philip Kiely
where else to find them
what they talk about
all 4 in the filters
where they keep going back
- AI Engineer World's Fair2 editions2024–2025
all 4 in the filters
on a stage with
- Pankaj Gupta2×
- Addy Osmanionce
- Aja Hammerlyonce
all 19 in the filters
who talks about the same things
- Pankaj Gupta7 talks
- Chris Fregly23 talks
- Sai KR Pentaparthi2 talks
- Aditya Lohia1 talk
- Legare Kerrison3 talks
- Nidhin Pattaniyil4 talks
| title | conference | date |
|---|---|---|
| From the main stage to the terminal | Google Cloud Next '26 | 2026-04-22 |
Gemini Enterprise Agent Platform now ships an end‑to‑end stack for building, scaling, governing and optimizing agents: Agent Development Kit… | ||
| Low-Precision Inference without Quality Loss... | PyTorch Conference 2025 | 2025-10-22 |
Claims that FP8 and NVFP4 microscaling cut latency and cost while preserving quality, with NVFP4 yielding ~30% model-size/accuracy efficiency and GEM kernels… | ||
| Introduction to LLM serving with SGLang | AI Engineer World's Fair 2025 | 2025-06-03 |
SGLang is an open-source serving framework that claims trillions of tokens per day in production and shows day‑zero support for models like DeepSeek and Qwen… | ||
| Optimizing inference for voice models in production | AI Engineer World's Fair 2025 | 2025-06-03 |
Demo uses Orpheus TTS (Llama 3.2 3B backbone) served with TensorRT-LLM + FP8 quantization and torch.compile on GPU for audio decoding, achieving ~150 ms TTFB… | ||
| The Golden Triangle of Inference Optimization: Balancing Latency, Throughput, and Quality | Optimized AI Conference 2025 | 2025-04-14 |
Baseten’s deck claims concrete wins: FP8 quantization on Lovelace/Hopper/Blackwell cuts bandwidth with preserved quality, distilling DeepSeek R1 671B into ~70B… | ||
| From model weights to API endpoint with TensorRT LLM | AI Engineer World's Fair 2024 | 2024-06-25 |
TensorRT-LLM is shown as a production-ready toolkit that converts Hugging Face weights into GPU-specific TensorRT engines and runs them via Triton or a custom… | ||
| nothing matches | ||