need to fix cuda compile. Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/python-type-check.yml
#	examples/speculative-simple/README.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-cuda/im2col.cu
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md

include/llama.h

@@ -861,6 +861,8 @@ extern "C" {
                           size_t   n_token_capacity,
                           size_t * n_token_count_out);
 
+#define LLAMA_STATE_SEQ_FLAGS_NONE 0
+
 // for backwards-compat
 #define LLAMA_STATE_SEQ_FLAGS_SWA_ONLY 1