sarvana7
95534bbfcc
Add Windows specifications for HP Z240
2026-02-22 13:34:40 -08:00
saravanakumardb1
6d18344fe0
docs(local-llms): add 7 RTX 5090 capability deep-dive guides
...
New capabilities/ subfolder with detailed guides:
- 01: GPU inference speed (benchmarks, Ollama tuning, API usage)
- 02: Whisper batch transcription (scripts, Python integration, use cases)
- 03: TTS generation at scale (Orpheus + Qwen3, batch scripts, voice cloning)
- 04: Fine-tuning / training (LoRA, QLoRA, data prep, Ollama export)
- 05: CUDA / TensorRT / ML research (toolchain setup, Triton kernels, profiling)
- 06: Stable Diffusion / image gen (ComfyUI, SDXL, FLUX, batch generation)
- 07: Multi-GPU workloads (scaling path, eGPU, cloud, cost planning)
- README: index with learning order and prerequisites
Each guide covers: what it is, how to use it, benefits, skills to learn
2026-02-21 20:36:21 -08:00
saravanakumardb1
1650e0da6c
docs(local-llms): add Mac vs Windows side-by-side comparison
...
Detailed comparison of MacBook Pro M4 Pro 48GB vs Razer Blade 18 RTX 5090:
- Hardware specs, memory architecture, VRAM budgets
- Model performance estimates (inference speed, capacity)
- Software dev capabilities (iOS, CUDA, Docker, etc.)
- Recommended workload distribution
- Visual ASCII diagrams for memory architecture
2026-02-21 17:59:58 -08:00
saravanakumardb1
efd45ad86f
feat(local-llms): add one-click Windows setup scripts
...
- setup-windows.ps1: PowerShell script for Windows side
- NVIDIA driver verification, Ollama install via winget
- Pull all 5 models with skip-if-exists logic
- WSL2 Ubuntu 24.04 install
- setup-wsl.sh: Bash script for WSL2 side
- Idempotent apt deps (Node.js 20, Python 3.12, ffmpeg, cmake)
- CUDA GPU passthrough verification
- Repo clone + git pull, whisper.cpp CUDA build
- Whisper model download, TTS setup, dashboard start
- README.md: 2-step quick start (no IDE required)
- setup-guide.md: add automated setup section at top
2026-02-21 16:28:02 -08:00
saravanakumardb1
b1d2e4ec81
fix(local-llms): cross-platform audit — 8 bugs/gaps fixed
...
- setup-tts.sh: make fully cross-platform (macOS + Linux/WSL2)
- OS detection, apt fallback, CUDA PyTorch install, nvidia-smi check
- cross-platform playback hints, HF_MIRROR env override
- api/system/route.ts: fix ffmpeg detection (use -version not --version)
- api/system/memory/route.ts: remove unused total variable in Linux path
- api/system/exec/route.ts: expand allowlist with Linux commands
(head, tail, grep, which, ps, uname, free, lscpu, nvidia-smi, etc.)
- api/tts/route.ts: cross-platform venv path + CUDA/MPS label
- api/whisper/route.ts: Linux binary/model paths
- api/ollama/logs/route.ts: Linux log paths + WSL2 hint
- test_qwen_tts.py: platform-aware speech text + CUDA device detection
- test_orpheus_tts.py: platform-aware text, move import sys to top
- setup-guide.md: fix false auto-detect claim, add HF_MIRROR hint
2026-02-21 15:27:49 -08:00
saravanakumardb1
f85b455eb5
ci: update CI/CD configuration
2026-02-21 14:13:07 -08:00
