fix: Prevent BMI2 instruction crash on AVX-only CPUs

[coffeerunhobby]

Description

Fix: Prevent BMI2 instruction crash on AVX-only CPUs
Problem
The llama-cpp-avx binary selection incorrectly runs on CPUs with AVX but without BMI2
(e.g., Intel Ivy Bridge). This causes crashes with "EOF" errors during model warmup
because the binary contains BMI2 instructions (shlx, mulx, etc.).

Notes for Reviewers

Solution:
Add BMI2 feature check before selecting the AVX binary. CPUs with AVX but without BMI2
now safely fall back to llama-cpp-fallback:

llama-cpp-fallback - x86_64 (SSE2 only)
llama-cpp-avx - AVX + no BMI2 (-mno-bmi -mno-bmi2)
llama-cpp-avx2 - AVX2 + FMA + BMI2 (unchanged)
llama-cpp-avx512 - AVX-512 (unchanged)

Testing:

• Intel Xeon E3-1240 V2 (AVX, no BMI2): now uses fallback
• Intel Haswell+ (AVX2 + BMI2): behavior unchanged

Affected CPUs

• Intel Sandy Bridge / Ivy Bridge (2011-2013)
• AMD Bulldozer / Piledriver (2011-2014)

Signed-off-by: Coffee Run Hobby 294crhwtf@mozmail.com

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	bd3ccbd
🔍 Latest deploy log	https://app.netlify.com/projects/localai/deploys/69583910b99e71000716ec14
😎 Deploy Preview	https://deploy-preview-7817--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[mudler]

Good catch, this looks good, however it fails on apple - would make sense to ignore the option when building on darwin