Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
19 lines
456 B
Python
19 lines
456 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
# Adapted from llama.py
|
|
"""Inference-only Phi3 model code inherit from Llama.py"""
|
|
|
|
from vllm.model_executor.models.llama import LlamaForCausalLM
|
|
|
|
|
|
class Phi3ForCausalLM(LlamaForCausalLM):
|
|
packed_modules_mapping = {
|
|
"qkv_proj": [
|
|
"qkv_proj",
|
|
],
|
|
"gate_up_proj": [
|
|
"gate_up_proj",
|
|
],
|
|
}
|