ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

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

Browse source 
* ggml: Add op l2_norm

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* ggml: Add op rwkv_wkv7

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: Add support for RWKV7 and ARWKV7 models

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: fix inference with RWKV6Qwen2

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: add more (a)rwkv7 variants in size

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Apply code-format changes

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* fix MUSA build

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* llama: fix shape error with rwkv using llama-parallel

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
This commit is contained in:
Molly Sophia 2025-03-18 07:27:50 +08:00 • committed by GitHub
parent 60c902926c
commit 7dfad387e3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
35 changed files with 2948 additions and 438 deletions
Download patch file Download diff file Expand all files Collapse all files

12
gguf-py/gguf/gguf_writer.py
View file

@ -767,6 +767,18 @@ class GGUFWriter:
def add_kv_lora_rank(self, length: int) -> None:
self.add_uint32(Keys.Attention.KV_LORA_RANK.format(arch=self.arch), length)
def add_decay_lora_rank(self, length: int) -> None:
self.add_uint32(Keys.Attention.DECAY_LORA_RANK.format(arch=self.arch), length)
def add_iclr_lora_rank(self, length: int) -> None:
self.add_uint32(Keys.Attention.ICLR_LORA_RANK.format(arch=self.arch), length)
def add_value_residual_mix_lora_rank(self, length: int) -> None:
self.add_uint32(Keys.Attention.VALUE_RESIDUAL_MIX_LORA_RANK.format(arch=self.arch), length)
def add_gate_lora_rank(self, length: int) -> None:
self.add_uint32(Keys.Attention.GATE_LORA_RANK.format(arch=self.arch), length)
def add_relative_attn_buckets_count(self, value: int) -> None:
self.add_uint32(Keys.Attention.REL_BUCKETS_COUNT.format(arch=self.arch), value)