popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

new tasks, model pricing, auto quantisation, etc...

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-06 17:11:53 +03:00
parent 7f67e29d76
commit ccb69c41e3
14 changed files with 466 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
packages/node/meshnet_node/startup.py
View File

@@ -52,6 +52,7 @@ def _max_assignable_layers(memory_mb: int, total_layers: int | None) -> int:
def _shard_budget_line(memory_mb: int, memory_source: str, total_layers: int | None, quantization: str) -> str:
memory_gb = memory_mb / 1024
gb_str = f"{memory_gb:.1f} GB"
budget_quantization = "bfloat16" if quantization == "auto" else quantization
if total_layers is None or total_layers <= 0:
return f"Memory budget: {gb_str} {memory_source}; shard budget: unknown model layer count"
max_layers = _max_assignable_layers(memory_mb, total_layers)
@@ -61,7 +62,7 @@ def _shard_budget_line(memory_mb: int, memory_source: str, total_layers: int | N
remaining_str = f"; {remaining_gb:.1f} GB remaining after full load" if remaining_gb > 1 else ""
return (
f"Memory budget: {gb_str} {memory_source}; "
f"Shard budget: up to {max_layers}/{total_layers} layers at {quantization}"
f"Shard budget: up to {max_layers}/{total_layers} layers at {budget_quantization}"
f"{remaining_str}"
)
@@ -306,7 +307,7 @@ def run_startup(
model_id: str | None = None,
shard_start: int | None = None,
shard_end: int | None = None,
quantization: str = "bfloat16",
quantization: str = "auto",
wallet_path: Path | None = None,
cache_dir: Path | None = None,
host: str = "127.0.0.1",