Files
xc-llm-ascend/vllm_ascend/patch/platform/patch_ec_connector.py
Li Wang 8d2998d0e4 [Misc] Upgrade vllm hash to 12_14 (#5000)
### What this PR does / why we need it?

### Does this PR introduce _any_ user-facing change?
1. fix https://github.com/vllm-project/vllm/pull/27938
2. fix https://github.com/vllm-project/vllm/pull/27145
pooling models now supports chunked prefill and prefix caching,
3. fix https://github.com/vllm-project/vllm/pull/30181
define the CPU fields in the field config where they really belong.
4. fix https://github.com/vllm-project/vllm/pull/28168
define the CPU fields in the field config where they really belong.
5. fix https://github.com/vllm-project/vllm/pull/30201
some moudle rename
6. fix https://github.com/vllm-project/vllm/pull/29067
fusedmoe moudle refactor
7. fix https://github.com/vllm-project/vllm/pull/29066
fusedmoe moudle refactor
8. fix https://github.com/vllm-project/vllm/pull/29624
### How was this patch tested?

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-12-15 19:54:23 +08:00

32 lines
1.3 KiB
Python

import vllm.distributed.ec_transfer.ec_connector.example_connector
from safetensors.torch import load_file
from vllm.distributed.ec_transfer.ec_connector.example_connector import (
ECConnectorMetadata, ECExampleConnector)
from vllm.logger import logger
class AscendECExampleConnector(ECExampleConnector):
def start_load_caches(self, encoder_cache, **kwargs) -> None:
metadata: ECConnectorMetadata = self._get_connector_metadata()
assert isinstance(metadata, ECConnectorMetadata)
assert encoder_cache is not None
if metadata is None:
logger.warning((
"In connector.start_load_caches, ",
"but the connector metadata is None",
))
return
# Load the EC for each mm data
for mm_data in metadata.mm_datas:
if mm_data.mm_hash in encoder_cache:
continue
filename = self._generate_filename_debug(mm_data.mm_hash)
ec_cache = load_file(filename)["ec_cache"].npu()
encoder_cache[mm_data.mm_hash] = ec_cache
logger.debug("Success load encoder cache for hash %s",
mm_data.mm_hash)
vllm.distributed.ec_transfer.ec_connector.example_connector.ECExampleConnector = AscendECExampleConnector