22a020e4c7
bitsandbytes quantizes on-the-fly: loads full bf16 weights (~54GB RAM peak) before compressing to int4. Kills the 40GB OptiPlex on torch.compile warmup. Fix in next commit: switch serve phase to llama.cpp + GGUF Q4_K_M. Pre-quantized weights load directly — peak RAM ~16GB, no compile overhead.
30 lines
1.0 KiB
YAML
30 lines
1.0 KiB
YAML
---
|
|
# ------------------------------------------------------------------------------
|
|
# FILE: roles/llm-inference/defaults/main.yml
|
|
# DESCRIPTION: Overridable defaults for the llm-inference role.
|
|
# Deploy target: astro-orbiter (Dell OptiPlex 7050 SFF, RTX 3090
|
|
# via OCuLink, Ubuntu 24.04.4 LTS).
|
|
# ------------------------------------------------------------------------------
|
|
|
|
# NVIDIA driver
|
|
llm_nvidia_driver_package: nvidia-driver-595-open
|
|
|
|
# Python venv
|
|
llm_venv_path: /home/jarvis/vllm-env
|
|
llm_venv_owner: jarvis
|
|
|
|
# HuggingFace
|
|
llm_hf_cache_dir: /home/jarvis/.cache/huggingface
|
|
llm_hf_model: google/gemma-2-27b-it
|
|
|
|
# vLLM serve
|
|
llm_serve_port: 8000
|
|
llm_serve_host: "0.0.0.0"
|
|
llm_quantization: "bitsandbytes" # int4 — fits 27B in 24GB VRAM (~14GB vs ~54GB bf16)
|
|
llm_gpu_memory_utilization: "0.92" # higher utilization to give KV cache room
|
|
llm_max_model_len: 4096 # safe ceiling given 15.96GB model + int4
|
|
|
|
# Monitoring
|
|
llm_gpu_exporter_version: "1.13.1"
|
|
llm_gpu_exporter_port: 9835
|