Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/intel.Dockerfile
#	.github/workflows/build-cross.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/release.yml
#	cmake/riscv64-spacemit-linux-gnu-gcc.cmake
#	docs/backend/OPENVINO.md
#	docs/backend/SYCL.md
#	docs/build-riscv64-spacemit.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	embd_res/ggml-vocab-qwen35.gguf
#	embd_res/ggml-vocab-qwen35.gguf.inp
#	embd_res/ggml-vocab-qwen35.gguf.out
#	examples/model-conversion/Makefile
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/common.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_reduce.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	ggml/src/ggml-zendnn/CMakeLists.txt
#	ggml/src/ggml-zendnn/ggml-zendnn.cpp
#	scripts/snapdragon/adb/run-completion.sh
#	tests/CMakeLists.txt
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/clip-impl.h
#	tools/mtmd/clip.cpp
#	tools/mtmd/clip.h
#	tools/server/README.md

examples/llama-eval/llama-eval.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# type: ignore
 
 import argparse
 import json
@@ -100,6 +99,8 @@ D) {D}
 
 
 class BaseDataset(ABC):
+    questions: List[Dict]
+
     @abstractmethod
     def get_question(self, index: int) -> Dict:
         pass
@@ -573,7 +574,7 @@ def normalize_number(s: str) -> Optional[int]:
 class AimeDataset(BaseDataset):
     def __init__(self, split: str = "train"):
         self.split = split
-        self.questions: List[Dict] = []
+        self.questions = []
         self._load_dataset()
 
     def _load_dataset(self):
@@ -618,7 +619,7 @@ class AimeDataset(BaseDataset):
 
 class Aime2025Dataset(BaseDataset):
     def __init__(self):
-        self.questions: List[Dict] = []
+        self.questions = []
         self._load_dataset()
 
     def _load_dataset(self):
@@ -681,7 +682,7 @@ class Aime2025Dataset(BaseDataset):
 class Gsm8kDataset(BaseDataset):
     def __init__(self, split: str = "test"):
         self.split = split
-        self.questions: List[Dict] = []
+        self.questions = []
         self._load_dataset()
 
     def _load_dataset(self):
@@ -742,7 +743,7 @@ class GpqaDataset(BaseDataset):
     def __init__(self, variant: str = "diamond", seed: int = 1234):
         self.variant = variant
         self.seed = seed
-        self.questions: List[Dict] = []
+        self.questions = []
         self._load_dataset()
 
     def _load_dataset(self):