Update readme; Format code; Add example yaml.

ktransformers/optimize/optimize_rules/DeepSeek-V2-Lite-Chat.yaml

@@ -13,7 +13,7 @@
     kwargs:
       generate_device: "cuda"
       prefill_device: "cuda"
-      generate_op: "KLinearQ8"
+      generate_op: "KLinearMarlin"
       prefill_op: "KLinearTorch"
 
 - match:
@@ -24,7 +24,7 @@
     kwargs:
       generate_device: "cpu"
       prefill_device: "cuda"
-      generate_op: "KLinearTorch"
+      generate_op: "KLinearMarlin"
       prefill_op: "KLinearTorch"
 
 - match:

ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat.yaml

@@ -14,7 +14,7 @@
     kwargs:
       generate_device: "cuda"
       prefill_device: "cuda"
-      generate_op: "KLinearQ8"
+      generate_op: "KLinearMarlin"
       prefill_op: "KLinearTorch"
 
 - match:
@@ -23,9 +23,9 @@
   replace:
     class: ktransformers.operators.linear.KTransformersLinear  # optimized Kernel on quantized data types
     kwargs:
-      generate_device: "cpu"
+      generate_device: "cuda"
       prefill_device: "cuda"
-      generate_op: "KLinearCPUInfer"
+      generate_op: "KLinearMarlin"
       prefill_op: "KLinearTorch"
 - match:
     name: "^model\\.layers\\..*\\.mlp$"

ktransformers/optimize/optimize_rules/rocm/DeepSeek-V3-Chat.yaml

@@ -0,0 +1,76 @@
+- match:
+    class: ktransformers.models.modeling_deepseek_v3.DeepseekV3RotaryEmbedding
+  replace:
+    class: ktransformers.operators.RoPE.YarnRotaryEmbeddingV3
+    kwargs:
+      generate_device: "cuda"
+      prefill_device: "cuda"
+
+- match:
+    name: "^lm_head$"  # regular expression 
+    class: torch.nn.Linear  # only match modules matching name and class simultaneously
+  replace:
+    class: ktransformers.operators.linear.KTransformersLinear  # optimized Kernel on quantized data types
+    kwargs:
+      generate_device: "cuda"
+      prefill_device: "cuda"
+      generate_op: "KLinearCPUInfer"
+      prefill_op: "KLinearTorch"
+
+- match:
+    name: "^model\\.layers\\.(?!.*self_attn\\.kv_b_proj).*$"  # regular expression 
+    class: torch.nn.Linear  # only match modules matching name and class simultaneously
+  replace:
+    class: ktransformers.operators.linear.KTransformersLinear  # optimized Kernel on quantized data types
+    kwargs:
+      generate_device: "cpu"
+      prefill_device: "cuda"
+      generate_op: "KLinearQ8"
+      prefill_op: "KLinearTorch"
+- match:
+    name: "^model\\.layers\\..*\\.mlp$"
+    class: ktransformers.models.modeling_deepseek_v3.DeepseekV3MoE
+  replace:
+    class: ktransformers.operators.experts.KDeepseekV3MoE     # mlp module with custom forward function
+    kwargs:
+      generate_device: "cuda"
+      prefill_device: "cuda"
+- match:
+    class: ktransformers.models.modeling_deepseek_v3.MoEGate
+  replace:
+    class: ktransformers.operators.gate.KMoEGate
+    kwargs:
+      generate_device: "cuda:0"
+      prefill_device: "cuda:0"
+- match:
+    name: "^model\\.layers\\..*\\.mlp\\.experts$"
+  replace:
+    class: ktransformers.operators.experts.KTransformersExperts     # custom MoE Kernel with expert paralleism
+    kwargs:
+      prefill_device: "cuda"
+      prefill_op: "KExpertsTorch"
+      generate_device: "cpu"
+      generate_op: "KExpertsCPU"
+      out_device: "cuda"
+  recursive: False # don't recursively inject submodules of this module
+- match:
+    name: "^model\\.layers\\..*\\.self_attn$"
+  replace:
+    class: ktransformers.operators.attention.KDeepseekV2Attention # optimized MLA implementation
+    kwargs:
+      generate_device: "cuda"
+      prefill_device: "cuda"
+      absorb_for_prefill: False # change this to True to enable long context(prefill may slower).
+- match:
+    name: "^model$"
+  replace:
+    class: "ktransformers.operators.models.KDeepseekV2Model"
+    kwargs:
+      per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
+- match:
+    name: "^model.embed_tokens"
+  replace:
+    class: "default"
+    kwargs:
+      generate_device: "cpu"
+      prefill_device: "cpu"