mrleo1nid/gpu-rent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update configuration and documentation for LLM support and local watchdog

Browse Source 
- Added `ollama-models.yaml` to .gitignore and implemented logic to copy it in gpu-rent.ps1 and gpu-rent.sh.
- Enhanced env.example to include new variables for LLM runtime options and local watchdog configuration.
- Updated CLI commands to support LLM options during setup and execution, including new flags for Ollama and llama.cpp.
- Improved documentation in cli.md and README.md to reflect changes in LLM integration and local watchdog functionality.
- Adjusted architecture and decisions documentation to clarify the role of LLMs and local watchdog in the system.
This commit is contained in:
Leonid Pershin
2026-08-21 05:29:23 +03:00
parent a9cf2e0f90
commit 2005b00175
43 changed files with 2258 additions and 197 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_session.py
+45 -31
View File
@@ -30,6 +30,32 @@ def _cfg(monkeypatch):
return load_config(require_auth=True)
def _mock_bind(monkeypatch):
monkeypatch.setattr(
"gpu_rent.session.ensure_floating_ip",
lambda conn, server, existing_id, existing_addr, log: ("203.0.113.9", "fip1"),
)
monkeypatch.setattr("gpu_rent.session.wait_ssh", lambda cfg, host, timeout=900.0: None)
monkeypatch.setattr(
"gpu_rent.session.run_ssh",
lambda cfg, host, command, **kw: (
"yes" if "gpu-rent-bootstrapped" in command else "inactive"
),
)
monkeypatch.setattr(
"gpu_rent.session.run_bootstrap",
lambda cfg, host, log, update=True, light=False: None,
)
monkeypatch.setattr("gpu_rent.session.provision_vm", lambda cfg, host, log, **kw: None)
monkeypatch.setattr("gpu_rent.session.wait_backend_idle", lambda cfg, host, log, **kw: None)
monkeypatch.setattr(
"gpu_rent.session.ensure_boot_snapshot",
lambda conn, boot_volume_id, cfg, log: None,
)
monkeypatch.setattr("gpu_rent.session.notify_ready", lambda cfg, log: None)
monkeypatch.setattr("gpu_rent.session.print_mcp_snippet", lambda cfg, log: None)
def test_cmd_up_refuses_zero_gpu_quota(monkeypatch):
monkeypatch.setattr("gpu_rent.session.connect", lambda cfg: object())
monkeypatch.setattr("gpu_rent.session.compute_quotas", lambda conn: {"gpu": 0})
@@ -42,24 +68,19 @@ def test_cmd_up_does_not_create_second_gpu(monkeypatch):
monkeypatch.setattr("gpu_rent.session.connect", lambda cfg: object())
monkeypatch.setattr("gpu_rent.session.compute_quotas", lambda conn: {"gpu": 1})
monkeypatch.setattr("gpu_rent.session.pick_existing_server", lambda conn: Server())
monkeypatch.setattr(
"gpu_rent.session.ensure_floating_ip",
lambda conn, server, existing_id, existing_addr, log: ("203.0.113.9", "fip1"),
)
monkeypatch.setattr("gpu_rent.session.wait_ssh", lambda cfg, host, timeout=420.0: None)
monkeypatch.setattr("gpu_rent.session.run_bootstrap", lambda cfg, host, log: None)
monkeypatch.setattr("gpu_rent.session.provision_vm", lambda cfg, host, log, **kw: None)
monkeypatch.setattr("gpu_rent.session.wait_backend_idle", lambda cfg, host, log, **kw: None)
monkeypatch.setattr(
"gpu_rent.session.ensure_boot_snapshot",
lambda conn, boot_volume_id, cfg, log: None,
)
monkeypatch.setattr("gpu_rent.session.notify_ready", lambda cfg, log: None)
monkeypatch.setattr("gpu_rent.session.print_mcp_snippet", lambda cfg, log: None)
_mock_bind(monkeypatch)
monkeypatch.setattr(
"gpu_rent.session.create_gpu_server",
lambda *a, **k: created.append("created") or Server(),
)
save_state(
SessionState(
server_id="s1",
floating_ip="203.0.113.9",
bootstrapped=True,
phase="ready_cloud",
)
)
state = cmd_up(_cfg(monkeypatch), yes=True)
assert created == []
assert state.server_id == "s1"
@@ -80,20 +101,7 @@ def test_cmd_up_unshelves_expired(monkeypatch):
"gpu_rent.session.unshelve",
lambda conn, server, log: unshelved.append(server.id) or Server(status="ACTIVE"),
)
monkeypatch.setattr(
"gpu_rent.session.ensure_floating_ip",
lambda conn, server, existing_id, existing_addr, log: ("203.0.113.9", "fip1"),
)
monkeypatch.setattr("gpu_rent.session.wait_ssh", lambda cfg, host, timeout=420.0: None)
monkeypatch.setattr("gpu_rent.session.run_bootstrap", lambda cfg, host, log: None)
monkeypatch.setattr("gpu_rent.session.provision_vm", lambda cfg, host, log, **kw: None)
monkeypatch.setattr("gpu_rent.session.wait_backend_idle", lambda cfg, host, log, **kw: None)
monkeypatch.setattr(
"gpu_rent.session.ensure_boot_snapshot",
lambda conn, boot_volume_id, cfg, log: None,
)
monkeypatch.setattr("gpu_rent.session.notify_ready", lambda cfg, log: None)
monkeypatch.setattr("gpu_rent.session.print_mcp_snippet", lambda cfg, log: None)
_mock_bind(monkeypatch)
monkeypatch.setattr(
"gpu_rent.session.create_gpu_server",
lambda *a, **k: created.append("created"),
@@ -108,8 +116,6 @@ def test_cmd_up_unshelves_expired(monkeypatch):
def test_cmd_stop_deletes_compute_keeps_disks(monkeypatch):
deleted = []
monkeypatch.setattr("gpu_rent.session.connect", lambda cfg: object())
monkeypatch.setattr("gpu_rent.session.pick_existing_server", lambda conn: Server())
monkeypatch.setattr(
"gpu_rent.session.delete_server",
lambda conn, server, log: deleted.append(server.id),
@@ -119,7 +125,13 @@ def test_cmd_stop_deletes_compute_keeps_disks(monkeypatch):
lambda conn, fip_id, address, log: deleted.append("fip"),
)
save_state(
SessionState(server_id="s1", boot_volume_id="b1", data_volume_id="d1", floating_ip="1.1.1.1")
SessionState(
server_id="s1",
boot_volume_id="b1",
data_volume_id="d1",
floating_ip="1.1.1.1",
bootstrapped=True,
)
)
class Conn:
@@ -129,10 +141,12 @@ def test_cmd_stop_deletes_compute_keeps_disks(monkeypatch):
return Server(server_id=sid)
monkeypatch.setattr("gpu_rent.session.connect", lambda cfg: Conn())
monkeypatch.setattr("gpu_rent.session.pick_existing_server", lambda conn: Server())
state = cmd_stop(_cfg(monkeypatch))
assert "s1" in deleted
assert state.phase == "idle"
assert state.server_id is None
assert state.bootstrapped is False
assert state.boot_volume_id == "b1"
assert state.data_volume_id == "d1"