690456dbf9
- Create nanovllm/ops/ module for low-level attention operators - Move chunked_attention.py from kvcache/ to ops/ - Update imports in full_policy.py (3 locations) - Fix: remove dead code in OffloadEngine.reset() referencing non-existent layer_k/v_buffer_a/b attributes Verified with needle test (32K offload): PASSED Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
20 lines
394 B
Python
20 lines
394 B
Python
"""
|
|
Operators module for nano-vLLM.
|
|
|
|
This module contains low-level attention operators and kernels.
|
|
"""
|
|
|
|
from nanovllm.ops.chunked_attention import (
|
|
flash_attn_with_lse,
|
|
merge_attention_outputs,
|
|
chunked_attention_varlen,
|
|
ChunkedPrefillState,
|
|
)
|
|
|
|
__all__ = [
|
|
"flash_attn_with_lse",
|
|
"merge_attention_outputs",
|
|
"chunked_attention_varlen",
|
|
"ChunkedPrefillState",
|
|
]
|