vLLM, every mention
4 scenes · ← back to vLLM
tap a year for its mentions
every year anyone Dylan Patel 8Matt Turck 3
Verbatim, from the transcripts: the passages where vLLM comes up
Dylan Patel: NVIDIA's New Moat & Why China is "Semiconductor Pilled”
- ▶ 10:33 Dylan Patel When you look at, for example, VLLM and SGLang, right? 7 times in the scene
- ▶ 38:49 Dylan Patel BLM and PyTorch, SGLang, and like all of these other like libraries and things that are just like, you know, and it goes to low level software, especially, right?
Making AI Work: Fine-Tuning, Inference, Memory | Sharon Zhou, CEO, Lamini
- ▶ 13:18 Matt Turck There seems to be a number of different companies doing different things, something you have together, something you have model, this open source project, like BLM, who, who does what? 2 times in the scene
- ▶ 23:24 Matt Turck I mean, I delivers 52 times more queries per second than VLLM, which we touch upon.