Branches - ggml-org/llama.cpp - Morph

SIGN IN SIGN UP

ggml-org / llama.cpp UNCLAIMED

LLM inference in C/C++

0 0 0 C++

BRANCHES

20 branches

master DEFAULT

0cc4m/server-memory-limit

0cc4m/test-backend-ops-model-load-hf

0cc4m/vulkan-async-fixes2

0cc4m/vulkan-flash-attention-dp4a

0cc4m/vulkan-mm-pipeline-selection

0cc4m/vulkan-repack

0cc4m/vulkan-slang-flash-attention

compilade/imatrix-neutral-prior

gg/attn-rot-rand

gg/attn-rot-wip

gg/ci-build-cro

gg/ggml-fix-rwkv-threads

gg/gguf-fix-division-by-zero

gg/release-disable-s390x

gg/scripts-eval

xsn/ai_policy_private_repo