Grant
64ce0fca10
Hardware dashboard:
- New hardware.py module: SSH probes each Spark for hostname, uptime, load+cores, RAM, disk, GPU (name, util, temp, power) + per-process GPU memory sum
- DGX Spark uses unified memory (nvidia-smi memory.total returns N/A); fall back to per-process compute memory and compute fraction against system RAM. Marks with gpu_unified_memory=true.
- 4s TTL cache in HardwareProbe to avoid hammering
- /api/hardware returns per-Spark snapshot
- UI: 'Spark hardware' section at the top with per-Spark cards (CPU load, RAM, GPU mem (unified), GPU util + temp + power, disk) — bars with warn threshold styling
- Polls every 8s
Knob context (tied to live hardware):
- Each Advanced knob now shows plain-English help text
- 'GPU memory %' shows '~N GB allocated · ~M GB left for OS/buffers' computed from actual Spark RAM
- 'Max context' shows '~N pages of text'
- Toggles show tradeoff descriptions
Explain context:
- '✨ Explain context' button on the update banner
- /api/explain-updates POST: forwards pending commits to the loaded vLLM model and streams its response back as SSE
- Renders into an expandable 'Explained by the loaded LLM' section under Pending commits
- Reasoning tokens shown italicized when the model emits them
Open WebUI integration:
- New 'Open WebUI URL' optional field in Configure Sparks
- /api/config exposes it; UI shows 'Open chat ↗' button in the top bar if set
Downloads:
- Third radio option: Spark 1 only / Spark 2 only / Both Sparks
- Backend picks SSH target based on mode
- HF repo link icon next to the input
- Helper line about NVFP4 for Blackwell
Model cards:
- Repo name is now a clickable link to its Hugging Face page
Package: bump 0.3.0:0
76 lines
2.4 KiB
Python
76 lines
2.4 KiB
Python
from __future__ import annotations
|
|
import os
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
|
|
|
|
def _env(name: str, default: str = "") -> str:
|
|
return os.environ.get(name, default)
|
|
|
|
|
|
def _resolve_models_yaml() -> str:
|
|
if env := os.environ.get("MODELS_YAML"):
|
|
return env
|
|
here = Path(__file__).resolve().parent # app/
|
|
candidates = [
|
|
here.parent / "models.yaml", # image/models.yaml (Docker)
|
|
here.parent.parent / "models.yaml", # <repo>/models.yaml (dev)
|
|
Path("/app/models.yaml"), # explicit container path
|
|
]
|
|
for p in candidates:
|
|
if p.exists():
|
|
return str(p)
|
|
return str(candidates[0]) # let load fail with a clear path
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class Settings:
|
|
spark1_host: str
|
|
spark1_user: str
|
|
spark2_host: str
|
|
spark2_user: str
|
|
parakeet_host: str
|
|
parakeet_user: str
|
|
parakeet_container: str
|
|
magpie_host: str
|
|
magpie_user: str
|
|
magpie_container: str
|
|
ssh_key_path: str
|
|
ssh_known_hosts: str
|
|
models_yaml: str
|
|
vllm_port: int
|
|
parakeet_port: int
|
|
magpie_port: int
|
|
bind_port: int
|
|
open_webui_url: str
|
|
|
|
@classmethod
|
|
def from_env(cls) -> "Settings":
|
|
spark2_host = _env("SPARK2_HOST")
|
|
spark2_user = _env("SPARK2_USER")
|
|
# Parakeet and Magpie default to Spark 2 unless explicitly overridden.
|
|
return cls(
|
|
spark1_host=_env("SPARK1_HOST"),
|
|
spark1_user=_env("SPARK1_USER"),
|
|
spark2_host=spark2_host,
|
|
spark2_user=spark2_user,
|
|
parakeet_host=_env("PARAKEET_HOST") or spark2_host,
|
|
parakeet_user=_env("PARAKEET_USER") or spark2_user,
|
|
parakeet_container=_env("PARAKEET_CONTAINER") or "parakeet-asr",
|
|
magpie_host=_env("MAGPIE_HOST") or spark2_host,
|
|
magpie_user=_env("MAGPIE_USER") or spark2_user,
|
|
magpie_container=_env("MAGPIE_CONTAINER") or "magpie-tts",
|
|
ssh_key_path=_env("SSH_KEY_PATH"),
|
|
ssh_known_hosts=_env("SSH_KNOWN_HOSTS"),
|
|
models_yaml=_resolve_models_yaml(),
|
|
vllm_port=int(_env("VLLM_PORT", "8888")),
|
|
parakeet_port=int(_env("PARAKEET_PORT", "8000")),
|
|
magpie_port=int(_env("MAGPIE_PORT", "9000")),
|
|
bind_port=int(_env("BIND_PORT", "9999")),
|
|
open_webui_url=_env("OPEN_WEBUI_URL", ""),
|
|
)
|
|
|
|
@property
|
|
def configured(self) -> bool:
|
|
return bool(self.spark1_host)
|