llama: Add support for RWKV v7 architecture(v2) #12412
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Molly Sophia <[email protected]>
Signed-off-by: Molly Sophia <[email protected]>
Signed-off-by: Molly Sophia <[email protected]>
Signed-off-by: Molly Sophia <[email protected]>
Signed-off-by: Molly Sophia <[email protected]>
github-actions
bot
added
testing
Signed-off-by: Molly Sophia <[email protected]>
Signed-off-by: Molly Sophia <[email protected]>
MollySophia
force-pushed
the
rwkv-v7-new
branch
from
560f606 to
35a8f06
Compare
Signed-off-by: Molly Sophia <[email protected]>
ggerganov
approved these changes
Mar 17, 2025
Rbiessy
approved these changes
Mar 17, 2025
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Mar 19, 2025
* ggml: Add op l2_norm Signed-off-by: Molly Sophia <[email protected]> * ggml: Add op rwkv_wkv7 Signed-off-by: Molly Sophia <[email protected]> * llama: Add support for RWKV7 and ARWKV7 models Signed-off-by: Molly Sophia <[email protected]> * llama: fix inference with RWKV6Qwen2 Signed-off-by: Molly Sophia <[email protected]> * llama: add more (a)rwkv7 variants in size Signed-off-by: Molly Sophia <[email protected]> * Apply code-format changes Signed-off-by: Molly Sophia <[email protected]> * fix MUSA build Signed-off-by: Molly Sophia <[email protected]> * llama: fix shape error with rwkv using llama-parallel Signed-off-by: Molly Sophia <[email protected]> --------- Signed-off-by: Molly Sophia <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
@BlinkDL 's explanation of RWKV v7:
RWKV-7 as a meta-in-context learner
Also there are plenty of tests on trained models posted on his x account.
Current available RWKV v7 model repos in HF format:
Base models:
https://huggingface.co/fla-hub/rwkv7-191M-world
https://huggingface.co/fla-hub/rwkv7-0.4B-world
https://huggingface.co/fla-hub/rwkv7-1.5B-world
https://huggingface.co/fla-hub/rwkv7-2.9B-world
https://huggingface.co/fla-hub/rwkv7-0.1B-g1 (Haven't add the option to enable it's capability yet.)
Distilled models:
https://huggingface.co/RWKV-Red-Team/ARWKV-R1-1B5
https://huggingface.co/RWKV-Red-Team/ARWKV-R1-7B
https://huggingface.co/RWKV-Red-Team/ARWKV_7B_R1_16K
This PR contains:
GGML_OP_L2_NORMthat applies pytorch-style l2 normalization, along the rows. Tested with CPU, CUDA, SYCL, Vulkan, Metal backends.GGML_OP_RWKV_WKV7which is the core of the RWKV v7 architecture. Implemented the naive recurrent wkv7 kernel in CPU, CUDA, SYCL, Vulkan, Metal.TODO:
#pragma unrollin wkv.cu fix the build.