mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
* support mm prefix caching * update code * fix mm_hashes * support encoder cache * add encoder cache * update code * update encoder cache * fix features bug * fix worker bug * support processor cache, need to optimize yet * refactor multimodal data cache * update code * update code * update v1 scheduler * update code * update code * update codestyle * support turn off processor cache and encoder cache * update pre-commit * fix code * solve review * update code * update code * update test case * set processor cache in GiB * update test case * support mm prefix caching for qwen model * fix code style check * update pre-commit * fix unit test * fix unit test * add ci test case * fix rescheduled bug * change text_after_process to prompt_tokens * fix unit test * fix chat template * change model path * [EP] fix adapter bugs (#4572) * Update expert_service.py * Update common_engine.py * Update expert_service.py * fix v1 hang bug (#4573) * fix import image_ops error on some platforms (#4559) * [CLI]Update parameters in bench latecy cli tool and fix collect-env cli tool (#4558) * add collect-env * del files * [Graph Optimization] Add dy_runnable and introduce cudagraph_switch_threshold for cudagraph mode switching (#4578) * add new branch for sot * reorder * fix batch bug * [XPU]Moe uses a new operator (#4585) * [XPU]Moe uses a new operator * [XPU]Moe uses a new operator * update response * [Feature] Support Paddle-OCR (#4396) * init * update code * fix code style & disable thinking * adapt for common_engine.update_mm_requests_chunk_size * use 3d rope * use flash_attn_unpadded * opt siglip * update to be compatible with the latest codebase * fix typo * optim OCR performance * fix bug * fix bug * fix bug * fix bug * normlize name * modify xpu rope * revert logger * fix bug * fix bug * fix bug * support default_v1 * optim performance * fix bug --------- Co-authored-by: root <root@szzj-acg-tge1-fdda9.szzj.baidu.com> Co-authored-by: zhangyue66 <zhangyue66@baidu.com> * [DataProcessor] add reasoning_tokens into usage info (#4520) * add reasoning_tokens into usage info initial commit * add unit tests * modify unit test * modify and add unit tests * fix unit test * move steam usage to processor * modify processor * modify test_logprobs * modify test_logprobs.py * modify stream reasoning tokens accumulation * fix unit test * perf: Optimize task queue communication from engine to worker (#4531) * perf: Optimize task queue communication from engine to worker * perf: get_tasks to numpy * perf: get_tasks remove to_numpy * fix: request & replace ENV * remove test_e2w_perf.py * fix code style --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> * Clean up ports after processing results (#4587) * [CI] Add /re-run command in PR comments to restart failed CI workflows (#4593) * [Others] api server exits when worker process is dead (#3271) * [fix] fix terminal hangs when worker process is dead * [chore] change sleep time of monitor * [chore] remove redundant comments * update docs --------- Co-authored-by: ApplEOFDiscord <wwy640130@163.com> Co-authored-by: ApplEOFDiscord <31272106+ApplEOFDiscord@users.noreply.github.com> Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com> Co-authored-by: yinwei <yinwei_hust@163.com> Co-authored-by: JYChen <zoooo0820@qq.com> Co-authored-by: qwes5s5 <45442318+qwes5s5@users.noreply.github.com> Co-authored-by: Ryan <zihaohuang@aliyun.com> Co-authored-by: yyssys <atyangshuang@foxmail.com> Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com> Co-authored-by: root <root@szzj-acg-tge1-fdda9.szzj.baidu.com> Co-authored-by: zhangyue66 <zhangyue66@baidu.com> Co-authored-by: kxz2002 <115912648+kxz2002@users.noreply.github.com> Co-authored-by: SunLei <sunlei5788@gmail.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> Co-authored-by: Zhang Yulong <35552275+ZhangYulongg@users.noreply.github.com> Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: 李泳桦 <39643373+liyonghua0910@users.noreply.github.com>
83 lines
3.8 KiB
Python
83 lines
3.8 KiB
Python
# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from fastdeploy.cache_manager.multimodal_cache_manager import EncoderCacheManager
|
|
from fastdeploy.engine.request import ImagePosition
|
|
|
|
|
|
def test_mm_encoder_cache():
|
|
max_encoder_cache = 4096
|
|
encoder_cache = EncoderCacheManager(max_encoder_cache=max_encoder_cache)
|
|
|
|
mm_hashes = ["mm_hash1", "mm_hash2"]
|
|
mm_positions = [ImagePosition(offset=120, length=400), ImagePosition(offset=620, length=800)]
|
|
|
|
cache_length = mm_positions[0].length + mm_positions[1].length
|
|
evict_hashes = encoder_cache.apply_cache(mm_hashes=mm_hashes, mm_items=mm_positions)
|
|
assert evict_hashes == [], "The evicted hashes should be empty."
|
|
assert list(encoder_cache.cache.keys()) == [
|
|
"mm_hash1",
|
|
"mm_hash2",
|
|
], "The cache should contain mm_hash1 and mm_hash2."
|
|
assert (
|
|
encoder_cache.current_cache_size == cache_length
|
|
), "The cache size should be the sum of the lengths of mm_hash1 and mm_hash2."
|
|
assert (
|
|
encoder_cache.current_cache_size <= max_encoder_cache
|
|
), "The cache size should be less than or equal to the max_encoder_cache."
|
|
|
|
mm_hashes = ["mm_hash3", "mm_hash4"]
|
|
mm_positions = [ImagePosition(offset=20, length=1204), ImagePosition(offset=1800, length=2048)]
|
|
cache_length += mm_positions[0].length + mm_positions[1].length - 400
|
|
evict_hashes = encoder_cache.apply_cache(mm_hashes=mm_hashes, mm_items=mm_positions)
|
|
assert evict_hashes == ["mm_hash1"], "The evicted hashes should be mm_hash1."
|
|
assert list(encoder_cache.cache.keys()) == [
|
|
"mm_hash2",
|
|
"mm_hash3",
|
|
"mm_hash4",
|
|
], "The cache should contain mm_hash2, mm_hash3, and mm_hash4."
|
|
assert (
|
|
encoder_cache.current_cache_size == cache_length
|
|
), "The cache size should be the sum of the lengths of mm_hash2, mm_hash3, and mm_hash4."
|
|
assert (
|
|
encoder_cache.current_cache_size <= max_encoder_cache
|
|
), "The cache size should be less than or equal to the max_encoder_cache."
|
|
|
|
evict_hashes = encoder_cache.apply_cache(mm_hashes=["mm_hash2"], mm_items=[ImagePosition(offset=620, length=800)])
|
|
assert evict_hashes == [], "The evicted hashes should be empty."
|
|
assert (
|
|
encoder_cache.current_cache_size == cache_length
|
|
), "The cache size should be the sum of the lengths of mm_hash2, mm_hash3, and mm_hash4."
|
|
assert (
|
|
encoder_cache.current_cache_size <= max_encoder_cache
|
|
), "The cache size should be less than or equal to the max_encoder_cache."
|
|
|
|
cache_length -= 1204
|
|
evict_hashes = encoder_cache.evict_cache(needed=800)
|
|
assert evict_hashes == ["mm_hash3"], "The evicted hashes should be mm_hash3."
|
|
assert list(encoder_cache.cache.keys()) == [
|
|
"mm_hash4",
|
|
"mm_hash2",
|
|
], "The cache should contain mm_hash2 and mm_hash4."
|
|
assert (
|
|
encoder_cache.current_cache_size == cache_length
|
|
), "The cache size should be the sum of the lengths of mm_hash2 and mm_hash4."
|
|
assert (
|
|
encoder_cache.current_cache_size <= max_encoder_cache
|
|
), "The cache size should be less than or equal to the max_encoder_cache."
|
|
|
|
encoder_cache.clear_cache()
|
|
assert encoder_cache.current_cache_size == 0, "The cache size should be 0."
|
|
assert list(encoder_cache.cache.keys()) == [], "The cache should be empty."
|