The letter

One letter a week, in your inbox.

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

b11310

October 1

cuda: guard the iq4_nl dequantize row kernel against short rows ( #29683 ) dequantize_block_iq4_nl writes QK_K values per block, but a row can be shorter than that (an IQ4_NL row is only guaranteed…

Read at llama.cpp releases ↗

More from llama.cpp releases on Accept All

More from llama.cpp releases on Accept All.