Skip to content

LLM inference in C/C++

C++ ggml

convert : write explicit recurrent_layers for Qwen3-Next / Qwen3.5 (#28208)

DevVexus9a7570587ce9
diff --git a/conversion/qwen.py b/conversion/qwen.py
index 419611896f..c7e0809f38 100644
--- a/conversion/qwen.py
+++ b/conversion/qwen.py
@@ -379,6 +379,13 @@ class Qwen3NextModel(_QwenMtpMixin, Qwen2MoeModel):
self.gguf_writer.add_ssm_group_count(self.hparams["linear_num_key_heads"])
self.gguf_writer.add_ssm_time_step_rank(self.hparams["linear_num_value_heads"])
self.gguf_writer.add_ssm_inner_size(self.hparams["linear_value_head_dim"] * self.hparams["linear_num_value_heads"])
+ if (layer_types := self.hparams.get("layer_types")) is not None:
+ n_layer = self.hparams["num_hidden_layers"]
+ if len(layer_types) != n_layer:
+ raise ValueError(f"layer_types has {len(layer_types)} entries, expected num_hidden_layers ({n_layer})")
+ recurrent = [t == "linear_attention" for t in layer_types]
+ recurrent += [False] * (self.block_count - n_layer)
+ self.gguf_writer.add_recurrent_layers(recurrent)
self.gguf_writer.add_full_attention_interval(self.hparams.get("full_attention_interval", 4))
if (rope_dim := self.hparams.get("head_dim")) is None:
rope_dim = self.hparams["hidden_size"] // self.hparams["num_attention_heads"]
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
index d51e459dda..d3a639f374 100644
--- a/gguf-py/gguf/constants.py
+++ b/gguf-py/gguf/constants.py
@@ -215,6 +215,7 @@ class Keys:
KV_LORA_RANK_SWA = "{arch}.attention.kv_lora_rank_swa"
SHARED_KV_LAYERS = "{arch}.attention.shared_kv_layers"
SLIDING_WINDOW_PATTERN = "{arch}.attention.sliding_window_pattern"
+ RECURRENT_LAYERS = "{arch}.attention.recurrent_layers"
TEMPERATURE_SCALE = "{arch}.attention.temperature_scale"
ROPE_PATTERN = "{arch}.attention.rope_pattern"
diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py
index 50e4d7c534..ed5a185b32 100644
--- a/gguf-py/gguf/gguf_writer.py
+++ b/gguf-py/gguf/gguf_writer.py
@@ -841,6 +841,9 @@ class GGUFWriter:
else:
self.add_array(key, value)
+ def add_recurrent_layers(self, value: Sequence[bool]) -> None:
+ self.add_array(Keys.Attention.RECURRENT_LAYERS.format(arch=self.arch), value)
+
def add_rope_pattern(self, value: Sequence[bool]) -> None:
self.add_array(Keys.Attention.ROPE_PATTERN.format(arch=self.arch), value)