Christian Puhrsch
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 1 in the filters
on a stage with
- Horace Heonce
who talks about the same things
one talk is not yet a subject
| title | conference | date |
|---|---|---|
| Accelerating Generative AI | PyTorch Conference 2023 | 2023-10-16 |
Native PyTorch pipelines compile and fuse real kernels to cut overhead and hit near memory bandwidth limits: baseline LLaMA‑7B goes from ~25 to 107 tokens/s… | ||
| nothing matches | ||