[mypy] Enable type checking for test directory (#5017)
This commit is contained in:
@@ -2,7 +2,7 @@ import argparse
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple
|
||||
from typing import Any, Callable, Dict, List, Optional, Tuple
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
@@ -19,7 +19,7 @@ def _prepare_hf_weights(
|
||||
quantized_model_dir: str,
|
||||
load_format: str = "auto",
|
||||
fall_back_to_pt: bool = True,
|
||||
) -> Tuple[str, List[str], bool]:
|
||||
) -> Tuple[List[str], bool]:
|
||||
if not os.path.isdir(quantized_model_dir):
|
||||
raise FileNotFoundError(
|
||||
f"The quantized model directory `{quantized_model_dir}` "
|
||||
@@ -94,7 +94,7 @@ def _hf_tensorfile_iterator(filename: str, load_format: str,
|
||||
|
||||
|
||||
def _kv_scales_extractor(
|
||||
hf_tensor_files: Iterable[str],
|
||||
hf_tensor_files: List[str],
|
||||
use_safetensors: bool,
|
||||
rank_keyword: str = "rank",
|
||||
expected_tp_size: Optional[int] = None) -> Dict[int, Dict[int, float]]:
|
||||
@@ -115,7 +115,7 @@ def _kv_scales_extractor(
|
||||
for char in rank_keyword:
|
||||
assert not char.isdecimal(
|
||||
), f"Rank keyword {rank_keyword} contains a numeric character!"
|
||||
rank_scales_map = {}
|
||||
rank_scales_map: Dict[int, Dict[int, float]] = {}
|
||||
for tensor_file in hf_tensor_files:
|
||||
try:
|
||||
rank_idx = tensor_file.find(rank_keyword)
|
||||
@@ -141,7 +141,7 @@ def _kv_scales_extractor(
|
||||
raise
|
||||
|
||||
if rank not in rank_scales_map:
|
||||
layer_scales_map = {}
|
||||
layer_scales_map: Dict[int, float] = {}
|
||||
rank_scales_map[rank] = layer_scales_map
|
||||
else:
|
||||
raise RuntimeError(
|
||||
@@ -222,7 +222,7 @@ def _metadata_extractor(quantized_model_dir: str,
|
||||
"does not exist.")
|
||||
metadata_files = glob.glob(os.path.join(quantized_model_dir, "*.json"))
|
||||
|
||||
result = {}
|
||||
result: Dict[str, Any] = {}
|
||||
for file in metadata_files:
|
||||
with open(file) as f:
|
||||
try:
|
||||
|
||||
@@ -5,7 +5,7 @@ distributively on a multi-nodes cluster.
|
||||
Learn more about Ray Data in https://docs.ray.io/en/latest/data/data.html
|
||||
"""
|
||||
|
||||
from typing import Dict
|
||||
from typing import Any, Dict, List
|
||||
|
||||
import numpy as np
|
||||
import ray
|
||||
@@ -40,8 +40,8 @@ class LLMPredictor:
|
||||
# The output is a list of RequestOutput objects that contain the prompt,
|
||||
# generated text, and other information.
|
||||
outputs = self.llm.generate(batch["text"], sampling_params)
|
||||
prompt = []
|
||||
generated_text = []
|
||||
prompt: List[str] = []
|
||||
generated_text: List[str] = []
|
||||
for output in outputs:
|
||||
prompt.append(output.prompt)
|
||||
generated_text.append(' '.join([o.text for o in output.outputs]))
|
||||
@@ -71,7 +71,7 @@ def scheduling_strategy_fn():
|
||||
pg, placement_group_capture_child_tasks=True))
|
||||
|
||||
|
||||
resources_kwarg = {}
|
||||
resources_kwarg: Dict[str, Any] = {}
|
||||
if tensor_parallel_size == 1:
|
||||
# For tensor_parallel_size == 1, we simply set num_gpus=1.
|
||||
resources_kwarg["num_gpus"] = 1
|
||||
|
||||
Reference in New Issue
Block a user