Windows native port: serve-mode pipe fix + RAM detection + POSIX guards, AVX-VNNI kernel, gated CUDA DLL (#131, fixes #123)

Rebased onto current dev, split into 3 logical parts (all validated):
1. CPU portability (serve-mode _O_BINARY pipe fix — stock main hangs on MinGW without it; RAM detection cap 0->9/layer; POSIX guards for select/mmap/madvise; warmup script).
2. AVX-VNNI 128-bit int8/int4 dot kernel (Alder Lake+/Meteor Lake+), bit-identical to AVX2 (author-verified on Meteor Lake; compiles out to AVX2 elsewhere) + _mm256_extracti128_si256 typo fix that blocked -march=native.
3. CUDA DLL via LoadLibrary, gated behind CUDA_DLL=1 (host never links cudart; silent CPU fallback if absent; author-verified on RTX 5070 Ti).

Validated here: make check 59/59, oracle 32/32 TF, Windows cross-compile clean + glm.exe loads+runs via WSL interop. Fixes the #123 Windows build failure.

.gitignore

@@ -11,15 +11,26 @@ desktop/src-tauri/gen/
 
 # binari compilati (si rigenerano con make / coli build)
 c/glm
+c/glm.exe
 c/olmoe
+c/olmoe.exe
 c/iobench
+c/iobench.exe
 c/tok_test
 c/backend_cuda.o
 c/backend_cuda_test
+c/backend_loader.o
+c/coli_cuda.dll
+c/coli_cuda.lib
+c/coli_cuda.exp
 c/tests/test_json
+c/tests/test_json.exe
 c/tests/test_st
+c/tests/test_st.exe
 c/tests/test_tier
+c/tests/test_tier.exe
 c/tests/test_grammar
+c/tests/test_grammar.exe
 
 # oracoli tiny generati (make_glm_oracle.py) e dati benchmark scaricati
 c/glm_tiny/