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

llama: add support for QRWKV6 model architecture (#11001)

Browse source 
llama: add support for QRWKV6 model architecture (#11001)

* WIP: Add support for RWKV6Qwen2

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

* RWKV: Some graph simplification

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

* Add support for RWKV6Qwen2 with cpu and cuda GLA

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

* RWKV6[QWEN2]: Concat lerp weights together to reduce cpu overhead

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

* Fix some typos

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

* code format changes

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

* Fix wkv test & add gla test

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

* Fix cuda warning

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

* Update README.md

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

* Update ggml/src/ggml-cuda/gla.cu

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Fix fused lerp weights loading with RWKV6

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

* better sanity check skipping for QRWKV6 in llama-quant

thanks @compilade

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: compilade <git@compilade.net>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: compilade <git@compilade.net>
This commit is contained in:
Molly Sophia 2025-01-10 09:58:08 +08:00 • committed by GitHub
parent c6860cc734
commit ee7136c6d1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 862 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

81
convert_hf_to_gguf.py
View file

@ -326,6 +326,7 @@ class Model:
gguf.MODEL_TENSOR.TIME_MIX_W2,
gguf.MODEL_TENSOR.TIME_MIX_DECAY_W1,
gguf.MODEL_TENSOR.TIME_MIX_DECAY_W2,
gguf.MODEL_TENSOR.TIME_MIX_LERP_FUSED,
gguf.MODEL_TENSOR.POSNET_NORM1,
gguf.MODEL_TENSOR.POSNET_NORM2,
)
@ -3316,6 +3317,8 @@ class Rwkv6Model(Model):
# required by llama.cpp, unused
self.gguf_writer.add_head_count(0)
lerp_weights: dict[int, dict[str, Tensor]] = {}
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
new_name = self.map_tensor_name(name)
@ -3331,14 +3334,84 @@ class Rwkv6Model(Model):
if new_name.endswith("time_mix_decay.weight") or "lerp" in new_name:
data_torch = data_torch.squeeze()
rescale_every_n_layers = self.hparams["rescale_every"]
if rescale_every_n_layers > 0:
if new_name.endswith("time_mix_output.weight") or new_name.endswith("channel_mix_value.weight"):
data_torch = data_torch.div_(2 ** int(bid // rescale_every_n_layers))
try:
rescale_every_n_layers = self.hparams["rescale_every"]
if rescale_every_n_layers > 0:
if new_name.endswith("time_mix_output.weight") or new_name.endswith("channel_mix_value.weight"):
data_torch = data_torch.div_(2 ** int(bid // rescale_every_n_layers))
except KeyError:
pass
# concat time_mix_lerp weights to reduce some cpu overhead
# also reduces the number of tensors in the model
if bid is not None and "time_mix_lerp" in new_name and "time_mix_lerp_x" not in new_name:
try:
self.lerp_weights[bid][new_name] = data_torch
except KeyError:
self.lerp_weights[bid] = {new_name: data_torch}
if all(f"blk.{bid}.time_mix_lerp_{i}.weight" in self.lerp_weights[bid].keys() for i in ["w", "k", "v", "r", "g"]):
new_name = f"blk.{bid}.time_mix_lerp_fused.weight"
data = torch.stack([self.lerp_weights[bid][f"blk.{bid}.time_mix_lerp_{i}.weight"].unsqueeze(0) for i in ["w", "k", "v", "r", "g"]], dim=0).unsqueeze(1)
yield (new_name, data)
return
yield (new_name, data_torch)
@Model.register("RWKV6Qwen2ForCausalLM")
class RWKV6Qwen2Model(Rwkv6Model):
model_arch = gguf.MODEL_ARCH.RWKV6QWEN2
def set_vocab(self):
try:
self._set_vocab_sentencepiece()
except FileNotFoundError:
self._set_vocab_gpt2()
def set_gguf_parameters(self):
block_count = self.hparams["num_hidden_layers"]
num_attention_heads = self.hparams["num_attention_heads"]
num_key_value_heads = self.hparams["num_key_value_heads"]
hidden_size = self.hparams["hidden_size"]
head_size = hidden_size // num_attention_heads
rms_norm_eps = self.hparams["rms_norm_eps"]
intermediate_size = self.hparams["intermediate_size"]
time_mix_extra_dim = 64 if hidden_size >= 4096 else 32
time_decay_extra_dim = 128 if hidden_size >= 4096 else 64
# RWKV isn't context limited
self.gguf_writer.add_context_length(1048576)
self.gguf_writer.add_embedding_length(hidden_size)
self.gguf_writer.add_block_count(block_count)
self.gguf_writer.add_wkv_head_size(head_size)
self.gguf_writer.add_time_mix_extra_dim(time_mix_extra_dim)
self.gguf_writer.add_time_decay_extra_dim(time_decay_extra_dim)
self.gguf_writer.add_feed_forward_length(intermediate_size)
self.gguf_writer.add_file_type(self.ftype)
# special parameters for time_mixing in RWKV6QWEN2
self.gguf_writer.add_layer_norm_rms_eps(rms_norm_eps)
self.gguf_writer.add_token_shift_count(1)
# RWKV6QWEN2 use grouped key/value like GQA
self.gguf_writer.add_head_count_kv(num_key_value_heads)
# required by llama.cpp, unused
self.gguf_writer.add_head_count(0)
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
for new_name, data in super().modify_tensors(data_torch, name, bid):
if "time_mix_w1" in new_name or "time_mix_w2" in new_name:
data = data.view(5, -1, data.shape[-1])
# rwkv6qwen2 has a different order of rkvwg instead of the original wkvrg
# permute them here to avoid code changes
data = torch.stack([data[3], data[1], data[2], data[0], data[4]], dim=0).view(-1, data.shape[-1])
if "w2" in new_name:
data = data.view(5, -1, data.shape[-1])
yield (new_name, data)
continue
yield (new_name, data)
@Model.register("MambaForCausalLM", "MambaLMHeadModel", "FalconMambaForCausalLM")
class MambaModel(Model):
model_arch = gguf.MODEL_ARCH.MAMBA