shawn
4e0ab94ee2
- Added start-llama-server.bat with cross-brand GPU auto-detection: * Detection 1: nvidia-smi for NVIDIA * Detection 2: WMIC for AMD, Intel Arc, Intel HD/Iris/UHD * Detection 3: vulkaninfo as final fallback probe * Falls back to CPU-only build when no GPU found - Downloaded llama-server b9947 builds: * Vulkan build (91 MB) - supports all GPU brands * CPU build (45 MB) - fallback in cpu/ subdir - Downloaded Qwen2.5-Coder-1.5B Q4_K_M model (1.1 GB) - Fixed run-hermes.bat polling: replaces fixed 5s timeout with curl-based readiness polling (up to 30 attempts, 1s apart) - All .bat files verified: ASCII text, CRLF line terminators - Added .gitignore for build artifacts and large binaries
33 lines
479 B
Plaintext
33 lines
479 B
Plaintext
# Build artifacts (large binaries, not tracked in git)
|
|
build/output/hermes-rescue.iso
|
|
build/output/casper-rw
|
|
build/output/hermes-data.ext4
|
|
build/output/fix-line-endings.ps1
|
|
build/iso-staging/
|
|
build/xubuntu-24.04*.iso
|
|
build/SHA256SUMS
|
|
build/hermes-build.fs
|
|
|
|
# Model and native binaries (large, downloaded at build time)
|
|
*.gguf
|
|
*.dll
|
|
*.exe
|
|
|
|
# Python cache
|
|
__pycache__/
|
|
*.pyc
|
|
*.pyo
|
|
|
|
# IDE/editor
|
|
.vscode/
|
|
.idea/
|
|
*.swp
|
|
*.swo
|
|
|
|
# OS
|
|
.DS_Store
|
|
Thumbs.db
|
|
|
|
# Secrets
|
|
src/hermes/auth.json
|