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

Refactor LLM configuration to remove llamacpp support

Browse Source 
- Removed references to llamacpp from configuration files, scripts, and documentation, streamlining the LLM setup process to focus solely on Ollama.
- Updated environment variables and paths to eliminate llamacpp-related entries, ensuring clarity in the configuration.
- Adjusted CLI commands and help messages to reflect the removal of llamacpp, enhancing user experience and reducing confusion.
- Revised documentation to provide clear guidance on using Ollama exclusively, including updates to setup instructions and runtime options.
This commit is contained in:
Leonid Pershin
2026-08-21 08:51:36 +03:00
parent 9a4b87dc06
commit 2ab32a8ab5
45 changed files with 139 additions and 1521 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/gpu_rent/ready.py
+6 -27
View File
@@ -95,7 +95,6 @@ def unit_active(name):
checks = []
want_swarm = WANT_SWARM
want_ollama = WANT_OLLAMA
want_llama = WANT_LLAMA
if want_swarm:
ok, detail = http_ok("http://127.0.0.1:7801/")
@@ -131,18 +130,6 @@ if want_ollama:
"unit": unit_active("gpu-rent-ollama"),
})
if want_llama:
ok, detail = http_ok("http://127.0.0.1:8080/health")
if not ok:
ok2, d2 = http_ok("http://127.0.0.1:8080/v1/models")
ok, detail = ok2, d2
checks.append({
"name": "llamacpp",
"ok": ok,
"detail": detail,
"unit": unit_active("gpu-rent-llamacpp"),
})
print(json.dumps({"checks": checks}, ensure_ascii=False))
'''
@@ -192,18 +179,17 @@ def wait_backend_idle(
)
def _expected_services(cfg: Config) -> tuple[bool, bool, bool]:
def _expected_services(cfg: Config) -> tuple[bool, bool]:
swarm = bool(getattr(cfg, "enable_swarmui", True))
rt = normalize_runtime(getattr(cfg, "llm_runtime", "none"))
return swarm, rt == "ollama", rt == "llamacpp"
return swarm, rt == "ollama"
def _probe_vm_once(cfg: Config, host: str) -> list[ServiceCheck]:
want_swarm, want_ollama, want_llama = _expected_services(cfg)
want_swarm, want_ollama = _expected_services(cfg)
script = (
_REMOTE_STACK_PROBE.replace("WANT_SWARM", "True" if want_swarm else "False")
.replace("WANT_OLLAMA", "True" if want_ollama else "False")
.replace("WANT_LLAMA", "True" if want_llama else "False")
)
out = run_ssh(
cfg,
@@ -251,8 +237,8 @@ def verify_stack_on_vm(
raise_on_fail: bool = True,
) -> list[ServiceCheck]:
"""Poll until every enabled service answers on the VM loopback."""
want_swarm, want_ollama, want_llama = _expected_services(cfg)
if not (want_swarm or want_ollama or want_llama):
want_swarm, want_ollama = _expected_services(cfg)
if not (want_swarm or want_ollama):
log("проверка стека: нечего ждать (swarm off, LLM none)")
return []
@@ -261,8 +247,6 @@ def verify_stack_on_vm(
names.append("SwarmUI :7801")
if want_ollama:
names.append("Ollama :11434")
if want_llama:
names.append("llama.cpp :8080")
log(f"проверка на VM: {', '.join(names)}")
deadline = time.time() + timeout
@@ -447,7 +431,7 @@ def verify_stack_local(
raise_on_fail: bool = True,
) -> list[ServiceCheck]:
"""After tunnel: local ports + light HTTP for enabled services."""
want_swarm, want_ollama, want_llama = _expected_services(cfg)
want_swarm, want_ollama = _expected_services(cfg)
targets: list[tuple[str, int, str | None]] = []
if want_swarm:
targets.append(("swarmui", int(cfg.swarmui_local_port), None))
@@ -459,9 +443,6 @@ def verify_stack_local(
f"http://127.0.0.1:{cfg.ollama_local_port}/api/tags",
)
)
if want_llama:
p = int(cfg.llamacpp_local_port)
targets.append(("llamacpp", p, f"http://127.0.0.1:{p}/health"))
if not targets:
return []
@@ -481,8 +462,6 @@ def verify_stack_local(
continue
if url:
ok, detail = _http_local(url)
if not ok and name == "llamacpp":
ok, detail = _http_local(f"http://127.0.0.1:{port}/v1/models")
last.append(ServiceCheck(name, ok, detail, "local"))
else:
ok, detail = _http_local(f"http://127.0.0.1:{port}/")