Update

[ghstack-poisoned]

Author: shoumikhin

backends/arm/MODELS.md

@@ -5,6 +5,7 @@
 - Conformer
 - Deep AutoEncoder
 - Deit Tiny
+- DeepSeek-R1-Distill-Qwen-1.5B
 - DeepLab v3 (DL3)
 - DS CNN
 - Inception v3 (IC3)

backends/arm/scripts/docgen/ethos-u/backends-arm-ethos-u-overview.md.in

@@ -48,8 +48,8 @@ See [Partitioner API](arm-ethos-u-partitioner.md) for more information of the Pa
 ## Quantization
 
 Since the Ethos-U backend is integer-only, all operators intended be executed on the NPU needs to be quantized. The Ethos-U quantizer supports
-[Post Training Quantization (PT2E)](https://docs.pytorch.org/ao/main/tutorials_source/pt2e_quant_ptq.html)  and
-[Quantization-Aware Training (QAT)](https://docs.pytorch.org/ao/main/tutorials_source/pt2e_quant_qat.html) quantization.
+[Post Training Quantization (PT2E)](https://docs.pytorch.org/ao/main/pt2e_quantization/pt2e_quant_ptq.html)  and
+[Quantization-Aware Training (QAT)](https://docs.pytorch.org/ao/main/pt2e_quantization/pt2e_quant_qat.html) quantization.
 
 For more information on quantization, see [Quantization](arm-ethos-u-quantization.md) <!-- @lint-ignore -->
 

backends/arm/test/models/DeepSeek_R1_Distill_Qwen/deepseek_r1_distill_qwen_test_config.py

@@ -0,0 +1,42 @@
+# Copyright 2026 Arm Limited and/or its affiliates.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+from transformers.models.qwen2.configuration_qwen2 import Qwen2Config
+
+
+def get_deepseek_r1_distill_qwen_1_5b_checkpoint_config() -> Qwen2Config:
+    config = Qwen2Config(
+        architectures=["Qwen2ForCausalLM"],
+        attention_dropout=0.0,
+        bos_token_id=151643,
+        eos_token_id=151643,
+        hidden_act="silu",
+        hidden_size=1536,
+        initializer_range=0.02,
+        intermediate_size=8960,
+        max_position_embeddings=131072,
+        max_window_layers=21,
+        num_attention_heads=12,
+        num_hidden_layers=28,
+        num_key_value_heads=2,
+        rms_norm_eps=1e-6,  # type: ignore[arg-type]
+        rope_parameters={
+            "rope_type": "default",
+            "rope_theta": 10000.0,
+        },
+        sliding_window=4096,
+        tie_word_embeddings=False,
+        transformers_version="4.44.0",
+        use_cache=True,
+        use_sliding_window=False,
+        vocab_size=151936,
+    )
+    config.update(
+        {
+            "torch_dtype": "bfloat16",
+            "use_mrope": False,
+        }
+    )
+    return config