-cpu flag

This commit is contained in:
Dobromir Popov
2026-07-09 08:19:15 +03:00
parent 4ed585bf54
commit 9ec4ca9ce1
8 changed files with 121 additions and 11 deletions

View File

@@ -212,6 +212,7 @@ class TorchModelShard:
shard_end: int,
quantization: Quantization = "auto",
cache_dir: Path | None = None,
force_cpu: bool = False,
) -> None:
if shard_start < 0 or shard_end < 0 or shard_start > shard_end:
raise ValueError("shard_start must be <= shard_end and non-negative")
@@ -229,7 +230,10 @@ class TorchModelShard:
) from exc
self.torch = torch
self.device = torch.device("cuda" if _torch_cuda_is_executable(torch) else "cpu")
if force_cpu:
self.device = torch.device("cpu")
else:
self.device = torch.device("cuda" if _torch_cuda_is_executable(torch) else "cpu")
load_source = str(cache_dir) if cache_dir is not None and (cache_dir / "config.json").exists() else model_id
quant_config, dtype, uses_quantized_weights = _model_load_plan(
AutoConfig,
@@ -682,8 +686,11 @@ def load_torch_shard(
shard_end: int,
quantization: Quantization = "auto",
cache_dir: Path | None = None,
force_cpu: bool = False,
) -> TorchModelShard:
return TorchModelShard(model_id, shard_start, shard_end, quantization, cache_dir)
return TorchModelShard(
model_id, shard_start, shard_end, quantization, cache_dir, force_cpu=force_cpu
)
def _total_layers_for_local_snapshot(auto_config: Any, load_source: str) -> int | None: