Docs - Upgrade version and release note

[polarG]

Release v0.12.0

Main Features & Improvements

SuperBench Enhancements

• Optimized cutlass build process for faster builds and smaller binaries (Dockerfile - Add cuda12.9 docker image #716)
• Updated image build pipeline (CI/CD - Update Image Build Pipeline #659)
• Added support for arm64 builds (Dockerfile - Add support for arm64 build #660, CI/CD - Add image build on arm64 arch #690)
• Upgraded pipeline dependencies (CI/CD - Upgrade dependency versions in pipeline #671)
• Fixed installation and lint issues (Setup - Fix installation and lint issues #684)
• Updated Flake8 repository (Flake8 repo from github #683)
• Added support for the latest Python versions (Init latest python support. #687)
• Enhanced error handling for pkg_resources imports (Lint: Enhancement of ignoring errors for import pkg_resources #692)
• Updated ROCm image build labels (CI/CD - Update label in the ROCm image build #693)
• Added CUDA 12.8 and CUDA12.9 support (Dockerfile - Support cuda12.8 for Blackwell arch #682, Dockerfile - Add cuda12.9 docker image #716)
• Consolidated multi-architecture Docker images (CI/CD - Merge multi-arch image #696)
• Updated runner OS to latest version (CI/CD - Update OS of runner to the latest. #702)

Micro-benchmark Improvements

• Added general CPU bandwidth and latency benchmarks (Benchmarks: micro benchmarks - add general CPU bandwidth and latency benchmark #662)
• Added nvbandwidth build and benchmark (Benchmarks: micro benchmarks - add nvbandwidth build #665, Benchmarks: micro benchmarks - add nvbandwidth benchmark #669)
• Added architecture support for 10.0 in gemm-flops (Microbenchmark: gemm-flops - Add arch support for 10.0 #680)
• Added GPU Stream micro benchmark (Benchmarks - Add GPU Stream Micro Benchmark #697)
• Added FP4 GEMM FLOPS support in cublaslt_gemm benchmark (Benchmarks - Add FP4 GEMM FLOPS support for cublaslt_gemm benchmark #711)
• Added Grace CPU support for CPU Stream benchmark (Benchmark - Add Grace CPU support for CPU Stream. #719)
• Fixed NUMA error on Grace CPU in gpu-copy benchmark (Bug Fix - Fix numa error on grace cpu in gpu-copy #658)
• Bumped onnxruntime-gpu dependency from 1.10.0 to 1.12.0 (Dependency - Bump onnxruntime-gpu version from 1.10.0 to 1.12.0 #663)
• Fixed stderr message in gpu-copy benchmark (Bug Fix - Fix stderr message in gpu-copy benchmark #673)
• Fixed TensorRT inference parsing (Bug - Fix tensorrt-inference parsing #674)
• Handled N/A values in nvbandwidth benchmark (Bugfix - nvbandwidth benchmark need to handle N/A value #675)
• Avoided unintended nvbandwidth function calls in all benchmarks (Bugfix: Avoid Unintended nvbandwidth Function Calls in All Benchmarks #685)
• Supported CUDA arch flag and autotuning in cublaslt GEMM (cuda arch flag for cublaslt #701, Benchmark - Support autotuning in cublaslt gemm #706)
• Revised CPU Stream benchmark (microbenchmark - CPU Stream Benchmark Revise #712)

Model Benchmark Improvements

• Added LLaMA-2 models (Benchmarks - Add LLaMA-2 Models #668)
• Added Mixture of Experts model (Benchmarks: Add Mixture of Experts Model  #679)
• Added DeepSeek inference benchmark (AMD GPU) (Benchmarks - Add deepseek megatron-lm benchmark #713)
• Fixed typos in documentation and code (Docs - Fix typos in documentation and code files #686)

Documentation Updates

• Updated CODEOWNERS file (Docs - Update CODEOWNERS #670, Update CODEOWNERS #718)

Result Analysis

• Enhanced logging for diagnosis rule baseline errors (Refactor: Enhance logging information for diagnosis rule op baseline errors. #689)

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 86.47%. Comparing base (e27491d) to head (0d436ba).
⚠️ Report is 1 commits behind head on release/0.12.

Additional details and impacted files

@@              Coverage Diff              @@
##           release/0.12     #727   +/-   ##
=============================================
  Coverage         86.47%   86.47%           
=============================================
  Files               102      102           
  Lines              7541     7541           
=============================================
  Hits               6521     6521           
  Misses             1020     1020           

Flag	Coverage Δ
cpu-python3.10-unit-test	71.59% <100.00%> (ø)
cpu-python3.12-unit-test	71.59% <100.00%> (ø)
cpu-python3.7-unit-test	70.65% <100.00%> (ø)
cuda-unit-test	83.98% <100.00%> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[abuccts]

please write the release note in the commit message or PR description, don't use an empty commit message