https://sujee.dev/tags/llm-inference/Recent content in Llm-Inference on sujee.devHugoen-usMon, 29 Jun 2026 00:00:00 +0000https://sujee.dev/events/2026-06-29_ai-engineer-sf/Mon, 29 Jun 2026 00:00:00 +0000https://sujee.dev/events/2026-06-29_ai-engineer-sf/<p>Gave a talk on <a href="../../speaking/optimizing-open-models-for-production/">Optimizing Open Models for Production</a> alongside Dylan Bristot.</p> <h2 id="resources">Resources</h2> <ul> <li><a href="https://www.ai.engineer/worldsfair/2026">AI Engineer World&rsquo;s Fair 2026</a></li> </ul> <h2 id="images">Images</h2>https://sujee.dev/events/2026-06-13_butterbase-hackathon/Sat, 13 Jun 2026 00:00:00 +0000https://sujee.dev/events/2026-06-13_butterbase-hackathon/<p>Supported Butter Base Hackathon in Sunnyvale, CA.</p> <h2 id="images">Images</h2>https://sujee.dev/events/2026-06-05_nvidia-hack-london/Fri, 05 Jun 2026 00:00:00 +0000https://sujee.dev/events/2026-06-05_nvidia-hack-london/<p>Supported the event through Token Factory, and I gave a kickoff talk on Token Factory and open models.</p> <p>Talk : <a href="../../speaking/building-with-open-models/">Building with open models</a></p> <h2 id="resources">Resources</h2> <ul> <li><a href="https://luma.com/NVIDIA-Hack-London">NVIDIA Hack for Impact London</a></li> </ul>https://sujee.dev/events/2026-04-28_nebius-berlin-build/Tue, 28 Apr 2026 00:00:00 +0000https://sujee.dev/events/2026-04-28_nebius-berlin-build/<p>Nebius Build Berlin. I gave a talk <a href="../../speaking/optimizing-open-models-for-production/">Optimizing Open Models for Production</a> alongside Dylan Bristot.</p> <h2 id="resources">Resources</h2> <h2 id="images">Images</h2> <kbd> </kbd>https://sujee.dev/events/2026-04-08_humanx/Wed, 08 Apr 2026 00:00:00 +0000https://sujee.dev/events/2026-04-08_humanx/<p>Talk: <a href="../../speaking/optimizing-open-models-for-production/">Optimizing Open Models for Production</a></p> <h2 id="images">Images</h2> <kbd> <a href="assets/2026-04__humanx-conference-1775676755655.png"><img src="assets/2026-04__humanx-conference-1775676755655.png" width="400px" alt="HumanX 2026 conference"></a> </kbd>https://sujee.dev/events/2026-03-26_datalab-webinar/Thu, 26 Mar 2026 00:00:00 +0000https://sujee.dev/events/2026-03-26_datalab-webinar/<p>Hosted a webinar on turning production LLM logs into better models — observability and evaluation techniques for inference workloads.</p> <h2 id="resources">Resources</h2> <ul> <li><a href="https://nebius.com/events/webinar-from-production-llm-logs-to-better-models">event page</a> - watch webinar replay</li> </ul>https://sujee.dev/events/2026-03-15_nebius-build-sf/Sun, 15 Mar 2026 00:00:00 +0000https://sujee.dev/events/2026-03-15_nebius-build-sf/<p>Very first event on the &lsquo;Nebius Build&rsquo; series - a pre-GTC workshop and hackathon in San Francisco. Organized / presented / supported the event. Ran a <a href="../../speaking/token-factory-workshop/">Token Factory workshop</a> and mentored builders.</p> <h2 id="resources">Resources</h2> <ul> <li><a href="https://nebius.com/events/nebius-build-sf">Nebius Build SF (event page)</a></li> <li>register: <a href="https://cerebralvalley.ai/e/nebius-build-sf">Cerebral Valley sign-up</a></li> </ul>https://sujee.dev/events/2026-02_post-training-webinar/Thu, 26 Feb 2026 00:00:00 +0000https://sujee.dev/events/2026-02_post-training-webinar/<p>Webinar on post-training techniques for running open-source LLMs in production.</p> <h2 id="resources">Resources</h2> <ul> <li><a href="https://nebius.com/events/webinar-post-training-for-production">Post-Training for Production (event page)</a> - watch webinar replay</li> </ul>https://sujee.dev/events/2025-12-10_ai-summit-nyc/Wed, 10 Dec 2025 00:00:00 +0000https://sujee.dev/events/2025-12-10_ai-summit-nyc/<p>Talk: <a href="../../speaking/optimizing-open-models-for-production/">Optimizing Open Models for Production</a></p>