Add support for DeepseekV2ForCausalLM (#7519)

* common : increase max number of experts to 160

* common : add tensors ATTN_Q_A, ATTN_Q_A_NORM, ATTN_Q_B, ATTN_KV_A_MQA, ATTN_KV_A_NORM, ATTN_KV_B needed by DeepSeek-V2 MLA (multi-head latent attention) architecture

* common : add model header parameters: leading_dense_block_count, expert_feed_forward_length, expert_shared_count, expert_weights_scale, attention.q_lora_rank, attention.kv_lora_rank, rope.scaling.yarn_log_multiplier

* convert-hf : add model conversion support for DeepseekV2ForCausalLM

* llama : add model types for DeepSeek-V2 and DeepSeek-V2-Lite models

* llama : add two new llm_build_moe_ffn() arguments: scale_w (whether to scale weights of selected MoE experts) and w_scale (numerical value of the scaling factor)

* llama : add inference support for LLM_ARCH_DEEPSEEK2

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>

1 files changed, 21 insertions, 0 deletions

diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py
index c194dd5d..b93747af 100644
--- a/gguf-py/gguf/gguf_writer.py
+++ b/gguf-py/gguf/gguf_writer.py
@@ -374,9 +374,15 @@ class GGUFWriter:
     def add_block_count(self, length: int) -> None:
         self.add_uint32(Keys.LLM.BLOCK_COUNT.format(arch=self.arch), length)
 
+    def add_leading_dense_block_count(self, length: int) -> None:
+        self.add_uint32(Keys.LLM.LEADING_DENSE_BLOCK_COUNT.format(arch=self.arch), length)
+
     def add_feed_forward_length(self, length: int) -> None:
         self.add_uint32(Keys.LLM.FEED_FORWARD_LENGTH.format(arch=self.arch), length)
 
+    def add_expert_feed_forward_length(self, length: int) -> None:
+        self.add_uint32(Keys.LLM.EXPERT_FEED_FORWARD_LENGTH.format(arch=self.arch), length)
+
     def add_parallel_residual(self, use: bool) -> None:
         self.add_bool(Keys.LLM.USE_PARALLEL_RESIDUAL.format(arch=self.arch), use)
 
@@ -407,6 +413,12 @@ class GGUFWriter:
     def add_expert_used_count(self, count: int) -> None:
         self.add_uint32(Keys.LLM.EXPERT_USED_COUNT.format(arch=self.arch), count)
 
+    def add_expert_shared_count(self, count: int) -> None:
+        self.add_uint32(Keys.LLM.EXPERT_SHARED_COUNT.format(arch=self.arch), count)
+
+    def add_expert_weights_scale(self, value: float) -> None:
+        self.add_float32(Keys.LLM.EXPERT_WEIGHTS_SCALE.format(arch=self.arch), value)
+
     def add_layer_norm_eps(self, value: float) -> None:
         self.add_float32(Keys.Attention.LAYERNORM_EPS.format(arch=self.arch), value)
 
@@ -416,6 +428,12 @@ class GGUFWriter:
     def add_causal_attention(self, value: bool) -> None:
         self.add_bool(Keys.Attention.CAUSAL.format(arch=self.arch), value)
 
+    def add_q_lora_rank(self, length: int) -> None:
+        self.add_uint32(Keys.Attention.Q_LORA_RANK.format(arch=self.arch), length)
+
+    def add_kv_lora_rank(self, length: int) -> None:
+        self.add_uint32(Keys.Attention.KV_LORA_RANK.format(arch=self.arch), length)
+
     def add_pooling_type(self, value: PoolingType) -> None:
         self.add_uint32(Keys.LLM.POOLING_TYPE.format(arch=self.arch), value.value)
 
@@ -440,6 +458,9 @@ class GGUFWriter:
     def add_rope_scaling_finetuned(self, value: bool) -> None:
         self.add_bool(Keys.Rope.SCALING_FINETUNED.format(arch=self.arch), value)
 
+    def add_rope_scaling_yarn_log_mul(self, value: float) -> None:
+        self.add_float32(Keys.Rope.SCALING_YARN_LOG_MUL.format(arch=self.arch), value)
+
     def add_ssm_conv_kernel(self, value: int) -> None:
         self.add_uint32(Keys.SSM.CONV_KERNEL.format(arch=self.arch), value)