corpus.blog
41,554 blogs · 5,181,941 posts Claim your blog
Record · corpus.blog/posts/01a08726-6fbd-7343-b457-48f69ced84bc

Optimizing Token Generation in llama.cpp's CUDA Backend

am17an.bearblog.dev · published 1 December 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at am17an.bearblog.dev Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
14
Words captured
982

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://github.com/ggml-org/llama.cpp/discussions/17621
github.com
https://github.com/ggml-org/llama.cpp/blob/fa0465954faef9d7170b967ad89f8bc5303a32f3/ggml/src/ggml-cuda/ggml-cuda.cu
github.com
https://github.com/ggml-org/llama.cpp/pull/16715
github.com
https://github.com/ggml-org/llama.cpp/pull/16130
github.com
https://github.com/ggml-org/llama.cpp/pull/14800
github.com
https://github.com/ggml-org/llama.cpp/pull/15631
github.com
https://github.com/ggml-org/llama.cpp/pull/14907
github.com
https://github.com/ggml-org/llama.cpp/pull/16991
github.com
https://github.com/JohannesGaessler
github.com
https://github.com/jeffbolznv
github.com
https://github.com/ggerganov
github.com
https://github.com/ORippler
github.com
https://github.com/CISC
github.com
https://gist.github.com/am17an/6833d30230b877c93abf33ca12a07937
gist.github.com