Enhance LLM configuration and installation scripts for improved flexibility

- Added new environment variables in `env.example` and `gpu-rent.vars.example` for fine-tuning LLM settings, including CUDA build options and model version pinning.
- Updated `llm.md` documentation to include detailed descriptions of new configuration options and usage cases for LLM setups.
- Enhanced the `provision.py` script to forward new environment variables during remote installations, improving the installation process for LLM components.
- Modified the `install_llamacpp.sh` script to support conditional CUDA builds and asset URL overrides, ensuring better compatibility with various environments.
- Improved logging in the installation scripts to provide clearer feedback during the setup process.

tests/test_remote_llm_env.py

@@ -0,0 +1,27 @@
+from types import SimpleNamespace
+
+from gpu_rent.provision import _LLAMACPP_INSTALL_ENV, _remote_llm_env
+
+
+def test_remote_llm_env_forwards_llamacpp_vars(monkeypatch):
+    monkeypatch.setenv("LLAMACPP_TAG", "b10545")
+    monkeypatch.setenv("LLAMACPP_BUILD_CUDA", "1")
+    monkeypatch.setenv("LLAMACPP_NGL", "40")
+    monkeypatch.setenv("LLAMACPP_ASSET_URL", "https://example/a.tar.gz")
+    monkeypatch.delenv("LLAMACPP_SHA256", raising=False)
+    cfg = SimpleNamespace(ssh_user="ubuntu")
+    env = _remote_llm_env(cfg, *_LLAMACPP_INSTALL_ENV)
+    assert env["SWARM_USER"] == "ubuntu"
+    assert env["LLAMACPP_TAG"] == "b10545"
+    assert env["LLAMACPP_BUILD_CUDA"] == "1"
+    assert env["LLAMACPP_NGL"] == "40"
+    assert env["LLAMACPP_ASSET_URL"] == "https://example/a.tar.gz"
+    assert "LLAMACPP_SHA256" not in env
+
+
+def test_remote_llm_env_skips_empty(monkeypatch):
+    for key in _LLAMACPP_INSTALL_ENV:
+        monkeypatch.delenv(key, raising=False)
+    cfg = SimpleNamespace(ssh_user="ubuntu")
+    env = _remote_llm_env(cfg, *_LLAMACPP_INSTALL_ENV)
+    assert env == {"SWARM_USER": "ubuntu"}