llama.cpp
llama: Add support for RWKV v7 architecture(v2)
#12412

Merged

llama: Add support for RWKV v7 architecture(v2) #12412

MollySophia merged 8 commits into ggml-org:master from MollySophia:rwkv-v7-new

ggml: Add op l2_norm

98eff126

ggml: Add op rwkv_wkv7

194ead5e

llama: Add support for RWKV7 and ARWKV7 models

ba7bdc0e

llama: fix inference with RWKV6Qwen2

f34ffbc1

llama: add more (a)rwkv7 variants in size

94b62e71

github-actions added testing

github-actions added Nvidia GPU

github-actions added Vulkan

github-actions added python

github-actions added ggml

github-actions added SYCL

github-actions added Apple Metal

Apply code-format changes

019120d0

fix MUSA build

35a8f068

MollySophia force pushed to 35a8f068 275 days ago

llama: fix shape error with rwkv using llama-parallel

8b32b8a2

MollySophia requested a review from

ggerganov 275 days ago

ggerganov approved these changes on 2025-03-17

Rbiessy approved these changes on 2025-03-17

MollySophia merged 7dfad387 into master 274 days ago

Reviewers

ggerganov

Rbiessy

Assignees

No one assigned

Labels

testing Nvidia GPU Vulkan python ggml SYCL Apple Metal

Milestone

No milestone