Morph MORPH
SIGN IN SIGN UP
ggml-org / llama.cpp UNCLAIMED

LLM inference in C/C++

0 0 58 C++

TP: fix 0-sized tensor slices, AllReduce fallback (#21808)

* TP: fix 0-sized tensor slices, AllReduce fallback

* fix layer structure <-> GPU count aliasing

* add missing std::fill

* fix CUDA device set, max ggml ctx size
J
Johannes Gäßler committed
fb19f94c715c466230c72d2a32822f8a9e113708
Parent: 7f251fd
Committed by GitHub <noreply@github.com> on 4/20/2026, 4:09:39 PM