hyunkyun moon
Employers on the program
- 2026Moreh2 talks
The year around now
Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.
Appearances by year
- PyTorch Conference
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| Apr 7, 2026 | PyTorch Conference Europe 2026 | PyTorch Conference | speaker | Birds of A Feather: Disaggregated Tokenization: Building Toward Tokens-In-Tokens-Out LLM Inference as Moreh LLMs are token-in, token-out - but our serving stacks aren't. Tokenization and preprocessing are still locked inside the inference engine, blocking the…Show lessLLMs are token-in, token-out - but our serving stacks aren't. Tokenization and preprocessing are still locked inside the inference engine, blocking the cache-aware routing and encode/prefill/decode (E/P/D) disaggregation that production deployments demand. To route smart, you need tokens before you... | |
| Apr 7, 2026 | PyTorch Conference Europe 2026 | PyTorch Conference | lightning talk | Lightning Talk: Not All Tokens Are Equal: Semantic KV-Cache for Agentic LLM Serving as Moreh Agentic AI workloads - tree-of-thought exploration, ReAct loops, hierarchical swarms - expose a fundamental mismatch in how we serve PyTorch models. Today's…Show lessAgentic AI workloads - tree-of-thought exploration, ReAct loops, hierarchical swarms - expose a fundamental mismatch in how we serve PyTorch models. Today's inference stacks treat the KV-cache as a flat, anonymous tensor buffer with blind LRU eviction. This ignores the structural reality of agents:... |
Frequent co-speakers
| Speaker | Shared events | Shared talks | Last together |
|---|---|---|---|
| Maroon Ayoub | 1 | 2 | 2026 |
| Hang Yin | 1 | 1 | 2026 |
| Nili Guy | 1 | 1 | 2026 |
| Xi Ning Wang | 1 | 1 | 2026 |
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.