Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,6 @@
def _apply_rerope_adapt_patches() -> None:
try:
_patch_attention_spec()
_patch_request_succeed_dumped_blocks()
_patch_utils()
_patch_gpu_model_runner()
_patch_qwen2_model()
Expand Down Expand Up @@ -83,23 +82,6 @@ def _page_size_bytes_rerope(self: "AttentionSpec") -> int:
)


# ==================== vllm/v1/request.py ====================
def _patch_request_succeed_dumped_blocks() -> None:
"""Patch Request to add succeed_dumped_blocks field."""
try:
from vllm.v1.request import Request

original_init = Request.__init__

def __init__(self, *args, **kwargs):
original_init(self, *args, **kwargs)
self.succeed_dumped_blocks = []

Request.__init__ = __init__
except ImportError:
logger.warning("Could not patch Request.__init__ - module not found")


# ==================== vllm/v1/attention/backends/utils.py ====================
def _patch_utils() -> None:
"""Patch common metadata"""
Expand Down