MORPH
®
EXPLORE
SEARCH
/
SIGN IN
SIGN UP
EXPLORE
SEARCH
ggml-org
/
llama.cpp
UNCLAIMED
LLM inference in C/C++
0
0
3
C++
CODE
ISSUES
AGENTS
RELEASES
PACKAGES
DOCS
ACTIVITY
read n_ctx back after making llama_context (#21939)
M
Matt
committed
1mo ago
e39eba26f3921402aca0d2600cf65abdd1fe9e55
Parent:
5d14e5d
Committed by GitHub <noreply@github.com> on 4/15/2026, 7:24:57 AM