llama.cpp, every mention
7 scenes · ← back to llama.cpp
tap a year for its mentions
every year anyone Michael Royzen 3Shawn Wang 2Omar Sanseviero 2Loubna Ben Allal 1
Verbatim, from the transcripts: the passages where llama.cpp comes up
⚡️ Google's Open AI Strategy — Omar Sanseviero, Google DeepMind
- ▶ 3:42 Omar Sanseviero So for example, we work with Lama CPP, Olama, MLX, Hogan Faces, BLM, NVIDIA, AMD. 2 times in the scene
2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- ▶ 1:04:41 Shawn Wang Like, unless you have something silly, like, okay, some, one form of standardization basically came from Georgi Gurganoff with Lama CPP.
Best of 2024: Synthetic Data / Smol Models, Loubna Ben Allal, HuggingFace [LS Live! @ NeurIPS 2024]
- ▶ 24:42 Loubna Ben Allal For example, there's MLX, MLC, Lama CPP, Transformers JS.
Building AGI with OpenAI's Structured Outputs API
- ▶ 16:25 Shawn Wang This is something that I saw, I first saw in Lama CPP, which seems to be the most, let's just say, academically permissive form of constraint.
The Winds of AI Winter (Q2 Four Wars of the AI Stack Recap)
- ▶ 28:07 unnamed speaker Llama CPP, MLX, those, those kinds are all sort of that layer.
Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
- ▶ 17:43 Michael Royzen Um, and my favorite example of this even today is kind of with, um, chadgpt browsing, where you can ask chadgpt browsing, um, how do I run llama.cpp? 2 times in the scene
- ▶ 1:05:25 Michael Royzen LLAMA CPP is great.