The letter

One letter a week, starting soon.

The week's signal, what shipped, what is worth running tonight, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

← Accept All   Archive
llama.cpp releasesTools

b12263

11.11

cuda : halve VMM pool reservation size and retry on cuMemAddressReserve failure ( #30542 ) cuda : Lowering VMM pool reservation size to 8 GB on GPUs with combined memory due to CUDA out of memory…

Chips & compute
Read at llama.cpp releases ↗

Related