Robert Shaw
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Michael Goinonce
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| llm-d: Kubernetes Native Distributed Inferencing | DevConf.US 2025 | 2025-09-19 |
llm-d serves LLMs by marrying VLM-style inference with Kubernetes: it implements continuous batching to pack per-step token work, manages massive KV cache page… | ||
| Optimizing vLLM Performance through Quantization | Ray Summit 2024 | 2024-09-30 |
vLLM adds practical quantization paths — activation quantization (FP8/INT8) and weight-only (W4/W8) — plus conversion kernels Marlin and Machete and a repo of… | ||
| nothing matches | ||