[refactor] Move FP16LayerPlanner and Q8_0LayerPlanner to quantized-specific subpackages

Author: orionpapadakis

…anner/quantization/FP16LayerPlanner.java …planner/model/fp16/FP16LayerPlanner.javasrc/main/java/org/beehive/gpullama3/tornadovm/layerplanner/quantization/FP16LayerPlanner.java renamed to src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/FP16LayerPlanner.java src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/quantization/FP16LayerPlanner.java renamed to src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/FP16LayerPlanner.java

@@ -1,19 +1,11 @@
-package org.beehive.gpullama3.tornadovm.layerplanner.quantization;
+package org.beehive.gpullama3.tornadovm.layerplanner.model.fp16;
 
 import org.beehive.gpullama3.tensor.GGMLType;
 import org.beehive.gpullama3.inference.state.State;
 import org.beehive.gpullama3.inference.weights.tornado.TornadoWeights;
 import org.beehive.gpullama3.model.Configuration;
 import org.beehive.gpullama3.model.Model;
-import org.beehive.gpullama3.tornadovm.layerplanner.base.QuantizedLayerPlanner;
-import org.beehive.gpullama3.tornadovm.layers.AbstractFFNLayers;
-import org.beehive.gpullama3.tornadovm.layers.Activation;
-import org.beehive.gpullama3.tornadovm.layers.type.fp16.LogitsFP16Layer;
-import uk.ac.manchester.tornado.api.GridScheduler;
-import uk.ac.manchester.tornado.api.ImmutableTaskGraph;
-
-import java.util.ArrayList;
-import java.util.List;
+import org.beehive.gpullama3.tornadovm.layerplanner.QuantizedLayerPlanner;
 
 /**
  * Base for all FP16-quantized layer planners.

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/GraniteFP16LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.GraniteTornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.granite.GraniteConfiguration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.FP16LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.ActivationGranite;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.GraniteFP16FFNLayers;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.LogitsGraniteFP16Layer;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/LlamaFP16LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.LlamaTornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.llama.LlamaConfiguration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.FP16LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.Activation;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.LlamaFP16FFNLayers;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.LogitsFP16Layer;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/MistralFP16LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.LlamaTornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.mistral.MistralConfiguration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.FP16LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.Activation;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.MistralFP16FFNLayers;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.LogitsFP16Layer;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/Phi3FP16LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.Phi3TornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.phi3.Phi3Configuration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.FP16LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.Activation;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.LogitsFP16Layer;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.Phi3FP16FFNLayers;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/Qwen2FP16LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.Qwen2TornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.qwen2.Qwen2Configuration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.FP16LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.Activation;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.LogitsFP16Layer;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.Qwen2FP16FFNLayers;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/fp16/Qwen3FP16LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.Qwen3TornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.qwen3.Qwen3Configuration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.FP16LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.Activation;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.LogitsFP16Layer;
 import org.beehive.gpullama3.tornadovm.layers.type.fp16.Qwen3FP16FFNLayers;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/q8_0/GraniteQ8_0LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.GraniteTornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.granite.GraniteConfiguration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.Q8_0LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.ActivationGranite;
 import org.beehive.gpullama3.tornadovm.layers.type.q8_0.GraniteQ8_0FFNLayers;
 import org.beehive.gpullama3.tornadovm.layers.type.q8_0.LogitsGraniteQ8_0Layer;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/q8_0/LlamaQ8_0LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.LlamaTornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.llama.LlamaConfiguration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.Q8_0LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.Activation;
 import org.beehive.gpullama3.tornadovm.layers.type.q8_0.LlamaQ8_0FFNLayers;
 import org.beehive.gpullama3.tornadovm.layers.type.q8_0.LogitsQ8_0Layer;

src/main/java/org/beehive/gpullama3/tornadovm/layerplanner/model/q8_0/MistralQ8_0LayerPlanner.java

@@ -4,7 +4,6 @@
 import org.beehive.gpullama3.inference.weights.tornado.LlamaTornadoWeights;
 import org.beehive.gpullama3.model.Model;
 import org.beehive.gpullama3.model.mistral.MistralConfiguration;
-import org.beehive.gpullama3.tornadovm.layerplanner.quantization.Q8_0LayerPlanner;
 import org.beehive.gpullama3.tornadovm.layers.Activation;
 import org.beehive.gpullama3.tornadovm.layers.type.q8_0.MistralQ8_0FFNLayers;
 import org.beehive.gpullama3.tornadovm.layers.type.q8_0.LogitsQ8_0Layer;