phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

chore: enable pyupgrade fixes (#1806)

Browse source 
# What does this PR do?

The goal of this PR is code base modernization.

Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)

Note to reviewers: almost all changes here are automatically generated
by pyupgrade. Some additional unused imports were cleaned up. The only
change worth of note can be found under `docs/openapi_generator` and
`llama_stack/strong_typing/schema.py` where reflection code was updated
to deal with "newer" types.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
This commit is contained in:
Ihar Hrachyshka 2025-05-01 17:23:50 -04:00 • committed by GitHub
parent ffe3d0b2cd
commit 9e6561a1ec
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
319 changed files with 2843 additions and 3033 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/models/llama/llama4/quantization/loader.py
View file

@ -6,7 +6,7 @@
import logging
import os
from typing import Callable, Optional
from collections.abc import Callable
import torch
from fairscale.nn.model_parallel.initialize import get_model_parallel_rank
@ -45,8 +45,8 @@ def experts_batched_swiglu_wrapper(
def convert_to_quantized_model(
model: Transformer,
checkpoint_dir: str,
quantization_mode: Optional[str] = None,
fp8_activation_scale_ub: Optional[float] = 1200.0,
quantization_mode: str | None = None,
fp8_activation_scale_ub: float | None = 1200.0,
use_rich_progress: bool = True,
) -> Transformer:
from ...quantize_impls import (
@ -213,7 +213,7 @@ def logging_callbacks(
)
task_id = progress.add_task("[blue]Converting layers...", total=total_blocks, status="Starting")
def update_status(message: Optional[str], completed: Optional[int] = None) -> None:
def update_status(message: str | None, completed: int | None = None) -> None:
if use_rich_progress:
if message is not None:
progress.update(task_id, status=message)