7707be8384
[Feature][KVCache] Implement Cache Manager V1 with GPU + CPU Cache Support (1/n) ( #7097 )
...
* [Feature][KVCache] Support cache manager v1 architecture
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
* Update cache manager and related modules
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
* chore: update cache_manager and related modules
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
* fix: add node to evictable set in complete_swap_to_device
When a node transitions from SWAP_TO_DEVICE to DEVICE via
complete_swap_to_device, it was not being added to the
_evictable_device set. This caused nodes with ref_count=0 to
become "orphaned" - not appearing in any evictable set despite
having cache_status=DEVICE.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
* feat: update cache manager v1 and related modules
- Add new cache_manager.py with cache management functionality
- Add radix_tree.py for prefix caching
- Update block_pool.py and metadata.py
- Update request.py and resource_manager_v1.py for scheduling
- Update gpu_model_runner.py for GPU model execution
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
* feat(cache): add cache controller v1 implementation
- Add CacheController class for cache management
- Update config.py with cache related configurations
- Refactor gpu_model_runner.py for improved cache handling
* feat(cache_manager): update cache manager v1
* fix(cache_manager): 修复 swap_cache H2D/D2H 方向的 block_ids 逻辑并清理 ForwardMeta
## Motivation
修复 swap_cache_optimized.cu 中 H2D 方向时 src/dst block_ids 使用错误的问题，
并清理 ForwardMeta 中已废弃的 cache_controller 字段。
## Modifications
- fix: swap_cache_optimized.cu 中根据 D2H 模板参数正确选取 src/dst block_ids，
修复 H2D 方向 src/dst 倒置 bug（同时修复 SwapCachePerLayerImpl 和 SwapCacheAllLayersBatchImpl）
- refactor: cache_manager/v1/__init__.py 将 LayerSwapTimeoutError 导入从
cache_controller 改为 cache_utils（正确来源）
- refactor: ForwardMeta 移除废弃的 cache_controller 字段
- refactor: gpu_model_runner.py 移除对应的 cache_controller 赋值语句
- test: 新增 tests/cache_manager/v1/test_swap_cache_ops.py 单元测试
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* feat(cache_manager): refactor cache manager v1 and optimize swap ops
## Motivation
对 cache manager v1 进行重构和优化，精简代码结构，提升可维护性。
## Modifications
- 重构 transfer_manager.py，大幅精简代码逻辑
- 优化 swap_cache_optimized.cu GPU 算子实现
- 调整 cache_manager.py、cache_controller.py 逻辑，修复 free_device_blocks 方法缺失问题
- 更新 block_pool.py、cache_utils.py、metadata.py、radix_tree.py
- 精简 gpu_model_runner.py、forward_meta.py、attention.py 中相关调用
- 更新对应单元测试（test_cache_controller、test_swap_cache_ops、test_transfer_manager）
- 调整 config.py 中相关配置项
* [KVCache][MTP] 支持 cache_manager_v1 下的 MTP KV Cache 初始化及多模态 hash
## Motivation
在 enable_cache_manager_v1 路径下，MTP（speculative decode）的 KV Cache 需要由
CacheController 统一管理，以复用 swap/transfer 能力，同时修复多模态场景下 block
hash 未携带 multimodal extra_keys 的问题。
## Modifications
- `cache_controller.py`
- 新增 `initialize_mtp_kv_cache`：通过 CacheController 初始化 MTP KV Cache，
并将其注册到 cache_kvs_map，使 transfer_manager 自动覆盖 MTP 层
- `initialize_host_cache` 中的 num_layers 改为包含 MTP 额外 cache 层数，保证
Host Cache 也为 MTP 分配足够空间
- `_free_gpu_cache` 改名为 `free_gpu_cache`（对外可调用）
- `cache_utils.py`
- 新增 `get_block_hash_extra_keys`：提取单个 block 内的多模态 hash 信息，
对齐 PrefixCacheManager 的 multimodal extra_keys 逻辑
- `get_request_block_hasher` 中在 hash_block_tokens 时携带 extra_keys，
修复多模态场景 prefix cache 命中率不准的问题
- `spec_decode/mtp.py`
- `update_mtp_block_num` 新增 `skip_cache_init` 参数，避免 v1 cache manager
路径下重复初始化 MTP KV Cache
- `gpu_model_runner.py`
- `initialize_kv_cache(v1)` 路径：在主模型 cache 初始化后，调用
`cache_controller.initialize_mtp_kv_cache` 完成 MTP cache 创建
- `clear_cache` / `wakeup` / `reset` 等路径：respect `enable_cache_manager_v1`
标志，跳过重复的 proposer.initialize_kv_cache 调用
## Usage or Command
```bash
# 启动支持 MTP + cache_manager_v1 的推理服务（示例）
bash run.sh
```
* fix(cache_manager): multi-GPU fix, mm hash boundary fix, and remove batch ops
1. Fix CuPy stream/event creation for multi-GPU: wrap all stream operations
with cp.cuda.Device(device_id) context to ensure streams/events are bound
to the correct device, preventing cross-device errors in multi-GPU setups.
2. Remove cudaSetDevice from SwapCacheAllLayers (handled by cupy context now).
3. Remove swap_cache_all_layers_batch op: simplified the implementation by
removing the batch upload variant; all-layer transfers now use the standard
swap_cache_all_layers with cupy device context.
4. Fix mm hash boundary comparison in get_block_hash_extra_keys: change
strict less-than (<) to less-than-or-equal (<=) so that multimodal items
ending exactly at block start are correctly excluded.
5. Extract config fields to KVCacheBase: model_config, cache_config,
quant_config, parallel_config are now set in the base class __init__ to
avoid duplication in CacheController and CacheManager subclasses.
6. Translate metadata.py docstrings from Chinese to English for broader
contributor accessibility.
7. Add test_cache_utils.py: comprehensive unit tests for
get_block_hash_extra_keys covering all boundary and overlap scenarios.
8. Expand test suite: test_request.py cache fields tests, test_radix_tree.py
backup candidate tests, test_transfer_manager.py and test_cache_manager.py
multi-GPU and concurrent operation tests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] fix List import and move write_policy normalization to CacheManager
## Motivation
修复两处问题：
1. `fastdeploy/engine/request.py` 中 `List` 未导入导致 pre-commit F821 报错
2. `write_policy` 归一化逻辑（`write_through` → `write_through_selective`）不应放在 `FDConfig`，移至 `CacheManager.__init__` 中，使其只影响 Cache Manager V1 的内部逻辑
## Modifications
- `fastdeploy/engine/request.py`: 在 `typing` 导入中补充 `List`，删除重复的 `CacheSwapMetadata` TYPE_CHECKING 导入，修复 F821/F811
- `fastdeploy/config.py`: 删除 `write_policy` 归一化逻辑
- `fastdeploy/cache_manager/v1/cache_manager.py`: 将归一化逻辑移入 `CacheManager.__init__`
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] fix pre-commit code style issues
## Motivation
修复 CI pre-commit 代码风格检查失败问题。
## Modifications
- `fastdeploy/engine/common_engine.py`: black 格式化
- `fastdeploy/worker/worker_process.py`: black 格式化 + isort 修复
- `fastdeploy/cache_manager/v1/storage/__init__.py`: isort 修复
- `fastdeploy/worker/gpu_worker.py`: isort 修复
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [Feature][KVCache] update cache_manager_v1 modules
## Motivation
更新 Cache Manager V1 相关模块，完善版权信息、改进模块结构与可维护性。
## Modifications
- `fastdeploy/cache_manager/v1/` 系列模块：补充版权 header，优化代码结构
- `fastdeploy/config.py`：配置项更新
- `fastdeploy/engine/sched/resource_manager_v1.py`：调度相关更新
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [Feature][KVCache] add BatchRequest.from_tasks and refactor worker task parsing
## Motivation
将 worker_process 中重复的 task 解析逻辑收敛到 BatchRequest，减少代码冗余，提升可维护性。
## Modifications
- `fastdeploy/engine/request.py`：新增 `BatchRequest.from_tasks()` 类方法，统一将 task_queue 任务分类为推理请求和控制请求
- `fastdeploy/worker/worker_process.py`：使用 `BatchRequest.from_tasks()` 替代内联解析逻辑，并修复重复的 control_reqs 处理块
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [Feature][KVCache] add NUMA affinity for host cache and skip swap cache tests
## Motivation
优化 Host cache 内存分配的 NUMA 亲和性，减少跨 NUMA 访问延迟；
同时跳过 swap cache ops 测试（当前环境不支持）。
## Modifications
- `fastdeploy/cache_manager/v1/cache_controller.py`：
- 新增 `_get_numa_node_for_gpu()` 方法，通过 nvidia-smi 或 sysfs 获取 GPU 对应的 NUMA 节点
- 新增 `_bind_to_closest_numa_node()` 方法，绑定当前线程到 GPU 最近的 NUMA 节点
- 在 `initialize_host_cache()` 中调用 NUMA 绑定，优化 H2D 传输性能
- `tests/cache_manager/v1/test_swap_cache_ops.py`：跳过所有测试类（`TestSwapCacheAllLayersCorrectness`、`TestSwapCacheAllLayersPerformance`、`TestSwapCacheRandomBlockIndices`）
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] fix unittest failures for cache_manager_v1
三个单测因接口变更或 Mock 方式问题导致失败，需修复。
- tests/distributed/chunked_moe.py：`setup_model_runner` 使用 `__new__` 跳过 `__init__`，补加 `enable_cache_manager_v1 = False`，修复 `AttributeError`
- tests/engine/test_resource_manager.py：`PrefixCacheManager` 为局部导入，`patch` 路径改为定义位置 `fastdeploy.cache_manager.prefix_cache_manager.PrefixCacheManager`
- tests/v1/test_resource_manager_v1.py：`_trigger_preempt` 第四参数已由 `list` 改为 `BatchRequest`，更新测试传参和断言
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] remove debug logging code
## Modifications
- fastdeploy/engine/request.py：删除调试用 logger 及 prompt_hashes 中的 debug 日志
- fastdeploy/worker/worker_process.py：删除 __main__ 中的调试 import 和 print 语句
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] fix cupy device id caching and pickle for _match_result
## Motivation
修复两个 bug：
1. `transfer_manager.py` 中每次调用 `cp.cuda.runtime.getDevice()` 存在隐患，应在初始化时缓存为实例变量，保证后续操作使用一致的设备 ID。
2. `request.py` 的 `__getstate__` 未跳过 `_match_result`，该字段包含 BlockNode 树的父子循环引用，pickle 时会触发 `RecursionError`；同时补充 `__setstate__` 确保 unpickle 后字段恢复为安全默认值。
## Modifications
- `transfer_manager.py`：初始化时调用 `cp.cuda.runtime.getDevice()` 并缓存到 `self._cupy_device_id`，后续 `with cp.cuda.Device(...)` 和日志均使用该缓存值。
- `request.py`：
- `__getstate__` 中将 `_match_result` 加入跳过集合 `_SKIP_KEYS`，避免循环引用导致 pickle 失败。
- 新增 `__setstate__`，unpickle 后将 `_block_hasher` 和 `_match_result` 恢复为 `None`。
## Usage or Command
* fix(test): fix unit test errors for _trigger_preempt and wakeup with MTP
- Use BatchRequest instead of list in test_trigger_preempt_records_tasks
- Add missing enable_cache_manager_v1 attr in TestSleepWakeupBehavior._make_runner
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] fix gpu_free_block_list returning wrong block IDs
## Motivation
`gpu_free_block_list` 的兼容 property 中误用了 `list(range(N))`，
将 `available_blocks()` 的返回值当作整数传给 `range()`，
导致返回 `[0, 1, ..., N-1]` 的假列表，而非真实的空闲 block ID。
## Modifications
- `cache_manager/v1/cache_manager.py`：将 `list(range(self._device_pool.available_blocks()))` 改为 `list(self._device_pool.available_blocks())`
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] 修复 gpu_free_block_list 返回 int 导致 TypeError
## Motivation
gpu_free_block_list 属性中调用 BlockPool.available_blocks()，
该方法返回 int（空闲块数量），用 list() 包装 int 会触发
TypeError: 'int' object is not iterable。
## Modifications
将 list(self._device_pool.available_blocks()) 改为
list(self._device_pool._free_blocks)，直接返回空闲块索引列表。
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [KVCache][CacheManager] 适配 V1 CacheManager 的 pause/sleep/free_cache 操作
## Motivation
V1 CacheManager 引入了新的 reset_cache() 接口，pause 和 sleep 操作需要适配，
同时 free_cache 需要支持可选的 clear_storage 参数。
## Modifications
- cache_controller.py: free_cache 新增 clear_storage 参数（默认 False），
仅当 clear_storage=True 时才调用 _clear_storage()，避免不必要的 storage 清空
- common_engine.py: pause 和 sleep 操作中，当 ENABLE_V1_KVCACHE_MANAGER 时
使用 cache_manager.reset_cache() 替代旧的 reset() 和 pause_transfer 逻辑
- gpu_model_runner.py: sleep 时仅在非 V1 cache manager 下执行 MTP cache 清除
## Usage or Command
# 启动服务（V1 CacheManager）
python -m fastdeploy.entrypoints.openai.api_server \
--enable-v1-kvcache-manager \
...
* [BugFix][KVCache] fix missing enable_cache_manager_v1 in test mocks and remove unused select_blocks_for_backup
- Remove unused `select_blocks_for_backup` method from radix_tree.py
- Fix `match_prefix` default param `skip_storage=True` and log order in cache_manager.py
- Sync test_gpu_model_runner.py with upstream/develop (add TestInsertTasksV1SplitwiseSuffix)
- Add `enable_cache_manager_v1=False` to all mock runners to fix AttributeError in CI
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [BugFix][KVCache] simplify _free_blocks in ResourceManagerV1 for non-v1 path
Remove redundant prefix_caching branch in else path; always call
recycle_gpu_blocks with full block_tables for non-cache-manager-v1 case.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* [KVCache][Optimization][BugFix] fix and optimize block_pool, cache_manager, transfer_manager, request
## Motivation
修复 cache_manager v1 中若干代码质量问题，提升性能并消除潜在的类型不一致 Bug。
## Modifications
1. **block_pool.py**：`BlockPool.allocate` 将逐个 pop 循环替换为切片 + 批量 set.update，消除 Python 循环开销，O(n) → O(k)（C 层批量操作）
2. **cache_manager.py**：`match_prefix` 在 prefix caching 关闭时提前 return 前写入空 `MatchResult()`，避免调用方解引用 `_match_result=None` 崩溃
3. **transfer_manager.py**：`_build_device_layer_indices` 在 `_cache_kvs_map` 为空时也重置四个层索引列表，防止残留旧 tensor 被 swap 算子使用
4. **request.py**：`BatchRequest.append_swap_metadata` / `append_evict_metadata` 构造 `CacheSwapMetadata` 时将 `src_type`/`dst_type` 从字符串改为 `CacheLevel` 枚举，与字段类型声明一致；补充 `CacheLevel` 导入；`match_result` 属性返回类型标注修正为 `Optional[MatchResult]`
5. **resource_manager_v1.py**：`_allocate_gpu_blocks` 日志从 `INFO` 降级为 `DEBUG`，消除高频调度路径的日志噪音
6. **tests/engine/test_request.py**：同步更新 `src_type`/`dst_type` 断言为 `CacheLevel` 枚举值，补充 `CacheLevel` 导入
## Usage or Command
单元测试：
```bash
source .venv/py310/bin/activate
cd baidu/FastDeploy
python -m pytest tests/cache_manager/v1/test_cache_manager.py -v
python -m pytest tests/cache_manager/v1/test_transfer_manager.py -v
python -m pytest tests/engine/test_request.py -v
```
* [BugFix][KVCache] Fix BlockPool.allocate returns all blocks when num_blocks=0
## Motivation
当 `allocate(num_blocks=0)` 被调用时，Python 负索引陷阱导致严重错误：
`-0 == 0`，所以 `self._free_blocks[-0:]` 等价于 `self._free_blocks[0:]`，
会返回并清空整个空闲块列表，而非返回空列表。
## Modifications
在 `BlockPool.allocate` 中增加对 `num_blocks == 0` 的提前判断，直接返回 `[]`，
避免触发 Python 负索引陷阱。
## Usage or Command
```bash
# 运行相关单元测试验证修复
python -m pytest tests/cache_manager/v1/test_cache_manager.py -vv -s
```
* [KVCache][Test] add unit tests for cache_manager v1 modules
## Motivation
补全 cache_manager/v1 各模块的单测覆盖，确保核心方法有完整的测试保障。
## Modifications
新增/补充以下测试文件，全部 326 个用例通过：
- tests/cache_manager/v1/test_block_pool.py（新建）
覆盖 BlockPool.get_metadata/set_metadata/resize、DeviceBlockPool/HostBlockPool
- tests/cache_manager/v1/test_metadata.py（新建）
覆盖 BlockNode、RadixTreeStats、MatchResult、CacheSwapMetadata、AsyncTaskHandler
- tests/cache_manager/v1/test_cache_utils.py（补充）
新增 hash_block_tokens、get_request_block_hasher、LayerDoneCounter 时间追踪及内部辅助方法
- tests/cache_manager/v1/test_radix_tree.py（补充）
新增 TestCompleteSwapToDevice 专项测试类（6 个用例）
- tests/cache_manager/v1/test_cache_manager.py（补充）
新增 offload_to_host、load_from_host、pending backup 系列、prepare_prefetch_metadata
- tests/cache_manager/v1/test_transfer_manager.py（补充）
新增 _swap_single_layer 校验路径、sync_input/output_stream、record_input_stream_event
## Usage or Command
```bash
# 运行所有新增单测
source .venv/py310/bin/activate
python -m pytest tests/cache_manager/v1/test_block_pool.py \
tests/cache_manager/v1/test_metadata.py \
tests/cache_manager/v1/test_cache_utils.py \
tests/cache_manager/v1/test_radix_tree.py \
tests/cache_manager/v1/test_cache_manager.py \
tests/cache_manager/v1/test_transfer_manager.py -v
# 期望结果：326 passed
```
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2026-04-21 14:39:00 +08:00
6e16438a57
[Feature] implement log channel separation and request log level system ( #7190 )
...
* feat: implement log channel separation and request log level system
* fix: log system improvements based on review
* add request_id to error logs, use RequestLogLevel enum, and unify logger implementation from utils to logger module
2026-04-16 15:13:05 +08:00
4fd877ed43
[Speculative Decoding] Support mtp expert-parallel and support different modality deploy ( #7018 )
...
* support mtp ep and support different modality
* fix default arg
2026-03-26 13:52:16 +08:00
bb881c2c0a
[PD Disaggregation] pd + cache_storage support vl model ( #6906 )
...
* pd + cache_storage support vl model
* support vl model
* fix test
2026-03-23 15:35:20 +08:00
f4a79d4c00
[Optimization]Unified data processing for online and offline ( #6891 )
...
* remove process_request
* fix chat
* fix unit test
* remove process response
* fix unit test
* fix offline decode
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com >
* fix sampling_params
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com >
2026-03-19 21:56:09 +08:00
c3d8db85c4
[Optimization] Update ZMQ server ( #6735 )
...
* add batch zmq send reaponse
* update
* Revert "update"
This reverts commit 0234a25b47163579578+Jiang-Jia-Jun@users.noreply.github.com >
2026-03-19 21:53:16 +08:00
3b7507a4c2
test_abort ( #6743 )
2026-03-17 14:06:40 +08:00
9f0778f991
[Feature] Support EP prefill with num_worst_tokens ( #6574 )
...
* support num worst tokens
* support num worst tokens
* fix build error
* support num worst tokens: fix errors
* support num worst tokens: fix feild
* support num worst tokens: delete requiements
* replace permute and depermute op by pure cuda
* replace permute and depermute op by pure cuda
* fix ci
* fix op
* fix nan
* fix code style
---------
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2026-03-11 17:09:07 +08:00
5d9524fc3c
[Models][Feature] Support new ERNIE reward model and add return_token_ids to reward API ( #6638 )
...
* reward model
* Add support for pooling-based inference in the reward model
* bugfix
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2026-03-06 18:51:00 +08:00
fa1906bd6f
[BugFix] Fix inaccurate cache hit rate and TTFT after request preemption ( #6620 )
...
* [chore] add has_been_rescheduled flag for requests
* [refactor] rename reschedule to preempted for accuracy and fix cache hit metrics
* [chore] add ttft_s
2026-03-05 16:25:02 +08:00
b7c5daa316
[RL] add pause, update_weights, resume interface for async RL ( #6052 )
...
* support dynamic run_control_request through zmq from apiserver to common_engine
* support pause/resume/is_paused/update_weights in apiserver->common_engine by common run_control_method
* change /is_puased from HTTP POST method to GET method
* add pause、resume、is_paused implementation
* support engine <==> worker communication(request&response)
* support sync weights through RDMA from checkpoint_transfer
* support specified version, rsync_config in update_weights rpc call
* add pause, update_weights, resume interface for async RL
* bug fix: update_weights support using default arguments
* fix typo
* typo fix
* typo fix
* typo fix
* add unitest for control request/response, localscheduler.get_inflight_requests, resource_manager_v1.preempted_all
* add "rsync" to LoadConfig.load_strategy Literal type hints
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* typo fix
* typo fix
* Apply suggestion from @Copilot
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* check version/rsync params
* add error log when version.txt not exists
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* raise specified ValueError when paramters check failed
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* tp barrier after run_control_method
* encode 'engine_worker_queue_port' to unique name of worker2engine fmq queue
* typo fix
* typo fix
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2026-01-23 10:18:07 +08:00
6e416c62dd
[Optimization] The pre- and post-processing pipeline do not perform dict conversion ( #5494 )
...
* to_request_for_infer initial commit
* refact to from_chat_completion_request
* preprocess use request initial commit
* bugfix
* processors refact to using request
* bug fix
* refact Request from_generic_request
* post process initial commit
* bugfix
* postprocess second commit
* bugfix
* serving_embedding initial commit
* serving_reward initial commit
* bugfix
* replace function name
* async_llm initial commit
* offline initial commit and fix bug
* bugfix
* fix async_llm
* remove add speculate_metrics into data
* fix logprobs bug
* fix echo bug
* fix bug
* fix reasoning_max_tokens
* bugfix
* bugfix and modify unittest
* bugfix and modify unit test
* bugfix
* bugfix
* bugfix
* modify unittest
* fix error when reasong_content is none for text_processor
* remove some unnessary logic
* revert removed logic
* implement add and set method for RequestOutput and refact code
* modify unit test
* modify unit test
* union process_request and process_request_obj
* remove a unit test
* union process_response and process_response_obj
* support qwen3_vl_processor
* modify unittest and remove comments
* fix prompt_logprobs
* fix codestyle
* add v1
* v1
* fix unit test
* fix unit test
* fix pre-commit
* fix
* add process request
* add process request
* fix
* fix
* fix unit test
* fix unit test
* fix unit test
* fix unit test
* fix unit test
* remove file
* add unit test
* add unit test
* add unit test
* fix unit test
* fix unit test
* fix
* fix
---------
Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com >
Co-authored-by: luukunn <981429396@qq.com >
Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com >
Co-authored-by: Zhang Yulong <35552275+ZhangYulongg@users.noreply.github.com >
2026-01-22 00:50:52 +08:00
b2a2e11551
[Feature] Support stopping the inference for the corresponding request in the online service after a disconnection request. ( #5320 )
...
* request disconnect
* request disconnect
* fix bug
* fix bug--amend
---------
Co-authored-by: root <root@yq01-sys-rpm26xc1knu.yq01.baidu.com >
2026-01-16 11:46:13 +08:00
e911ac2ce7
[BugFix] Refine the preparation of cpu and storage cache ( #5777 )
...
* Refine the preparation of cpu and storage cache
* fix error
* fix error
* up
* fix
* up docs
* fix unittest
* remove debug info
2026-01-05 10:13:30 +08:00
412867fd99
[Feature] Support KV Cache Storage ( #5571 )
...
* Support Mooncake Store
* up
* up
* add op
* fix conflict
* fix error
* up for comments
* avoid thread lock
* up
* fix unittest
* fix unittest
* remove debug info
* consider tp_size > 1
* add default rdma_nics
* add utils
* up
* fix error
---------
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2025-12-25 16:30:35 +08:00
be3be4913a
[Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM ( #5195 )
...
* [Optimization] refactor(chat_handler,completion_handler): extract base classes and use AsyncLLM
* [Optimization] refactor(chat_handler,completion_handler): rename class
2025-12-25 16:28:15 +08:00
85db9d5e56
[Others] reschedule preempt task support optional func ( #5649 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
* [Others] reschedule preempt task support optional func
* fix bug
* fix bug
2025-12-23 20:45:52 +08:00
a30b4da260
[Feature] Tracing: Fine-Grained Tracing for Request Latency Part1 ( #5458 )
2025-12-16 16:36:09 +08:00
909059c60a
[Feature] Support for request-level speculative decoding metrics monitoring. ( #5518 )
...
* support spec metrics monitor per request
* fix bug
* remove debug log
* fix ut bugs
2025-12-12 12:22:18 +08:00
76649b45c1
[Optimization] compulte real max_logprobs in batch ( #5430 )
2025-12-09 14:15:05 +08:00
5d9b5e4a5b
[Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication ( #4868 )
...
* Refactor async_llm:cross-process with EngineService
* fix: async_llm output process
* fix: return prompt_token_ids and prompt_tokens in first res
* optimize common_engine start func
2025-12-09 10:53:40 +08:00
2f208db4e9
[Feature] Multimodal Model P / D Separation ( #5323 )
...
* RouterArgs port str -> int
* fix race condition [is_fetching] causing multiple fetch requests
* bugfix: Delete duplicate input_ids tensor creation
* mm pd splitwise json -> pickle5; multimodal_inputs only pos id;
debuglog f to %s
* fix ENABLE_V1_KVCACHE_SCHEDULER=0 mm model lack pos_id, ...
* update cr
* Apply suggestions from code review
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* pre-commit fix
* rm multimodal_inputs deepcopy & fix rdma_cache_transfer.py tpsize=0
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-09 10:47:42 +08:00
a8ffc22032
[BugFix] fix init RequestOutput ( #5419 )
...
* fix init RequestOutput
* up
* fix
* fix
2025-12-09 10:20:22 +08:00
80efe98f8d
[PD Disaggregation] Add timestamp for analyzing splitwise deployment ( #5317 )
...
* Add timestamp for analyzing splitwise deployment
* up
* up
* up
* up
* up
* up
* fix format
* fix
2025-12-08 10:08:44 +08:00
c9d7f9e7c3
[BugFix] fix async download bug ( #5349 )
...
* fix async download bug
* update log
* Revert "update log"
This reverts commit 5816e602f4
2025-12-05 18:59:12 +08:00
5f8d4aedea
[Feature] support audio tts ( #5333 )
2025-12-03 21:06:48 +08:00
c563eca791
[Feature] support reward model ( #5301 )
...
* Your commit message here
* add test
* update develop
* support reward
* support enable_chunk_prefill
* support bingfa
* support convert is reward
* update test
* delete print
* fix enable_thinking
* add document
* fix place
* fix test
* fix
* support enable_prefix_caching
* add no-enable_prefix-caching test
* fix
* support enable_prefix_caching
* delete print
* fix document
* fix
* fix test
* fix document and delete chinese
* udpate
* enable_thinking
* fix test
2025-12-02 14:55:31 +08:00
117980dd4e
[LogProbs]Enable prompt logprobs output and modify data transmission method for the online interface. ( #5089 )
...
* add prompt logprobs
* Merge prompt_logprobs_tensors and prompt_logprobs
* fix param check
* trigger ci
* fix unitest
* fix logprobs bug
2025-12-02 13:49:51 +08:00
8aec3acc8c
fix mm type bug ( #5300 )
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
2025-11-29 20:48:14 +08:00
c424e08dc5
[Speculative Decoding] split draft_tokens into standalone post-processing path ( #5205 )
...
* refactor(mtp): split draft_tokens into standalone post-processing path for MTP + logprobs
* Restore Request.__repr__ implementation
* ci
* add envs
* fix unittest
2025-11-27 11:22:41 +08:00
cead6b26fa
[Metrics] Update time_to_first_token to include tokenization & queue time, and remove redundant metrics ( #4993 )
...
* [update] update time_to_first_tokens to include queue time, and remove first_token_latency and infer_latency
* [doc] update docs
* [ci] fix test
* [chore] delete redundant code
---------
Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com >
2025-11-26 14:42:17 +08:00
df2be1cf16
[BugFix] fix mm_positions type error ( #5182 )
...
* fix mm_positions type error
* update code
* update code
* update code
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-11-25 19:28:18 +08:00
3ea1b44a58
[Optimization] Improve perf for fd response token with internal adapter ( #4992 )
...
* [Optimize] Improve perf for fd response token with internal adapter
* fix
* fix bug
* fix ci
* fix ci
* fix ci
* fix ci
2025-11-21 19:02:03 +08:00
d2298dcb0c
[Polish] Simplify __repr__ method in Request class ( #5153 )
...
Remove detailed string representation for Request class.
2025-11-21 17:21:06 +08:00
109d48e456
[Feature] support async download features ( #5003 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
* support async download features
* add test case
* update code
2025-11-19 22:23:36 +08:00
36822fa49c
[PD Disaggregation] remove splitwise deployment on single node and refine the code ( #4891 )
...
* remove splitwise deployment on single node and refine the code
* up
* up
* up
* add test
* up
2025-11-14 09:56:53 +08:00
a2d06118e1
[Logprobs]Support prompt_logprobs and max_logprobs ( #4897 )
...
* add prompt logprobs
* trigger ci
* fix unitest
* Update fastdeploy/config.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update fastdeploy/entrypoints/llm.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update fastdeploy/engine/sampling_params.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update tests/engine/test_sampling_params.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update tests/engine/test_sampling_params.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* fix max_logprobs
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-11-12 19:29:48 +08:00
78895e2c7d
[Bug Fix] fix bug for PD EP ( #4823 )
...
* fix bug for PD EP
* fix
* optimize perf for engine worker queue
* fix bug
* fix internode ll two stage
* fix for ci
* fix bug
2025-11-10 15:33:29 +08:00
08ca0f6aea
[Feature] [PD] add simple router and refine splitwise deployment ( #4709 )
...
* add simple router and refine splitwise deployment
* fix
2025-11-06 14:56:02 +08:00
cc8f5312f5
[Feature] Add timestamp for profiler ( #4726 )
...
* [Feature] Add timestamp for profiler
* fix bug for offine inference
* fix for ci
* fix
* fix ci
2025-11-05 12:04:59 +08:00
7dc9d9885e
[BugFix] fix offline llm chat "enable_thinking" is always "False" ( #4686 )
...
* fix enable_thinking
* recover ernie4_5_vl_processor
2025-10-30 19:45:41 +08:00
14f8cddaf1
[Feature] add mm token usage ( #4570 )
...
* add mm token usage
* fix unit test
* fix unit test
* fix unit test
* fix model path
* fix unit test
* fix unit test
* fix unit test
* remove uncomment
* change var name
* fix code style
* fix code style
* fix code style
* fix code style
* fix unit test
2025-10-29 14:37:12 +08:00
14e7d88ea4
[feature] support reward api ( #4518 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
Co-authored-by: SunLei <sunlei5788@gmail.com >
2025-10-29 00:20:28 +08:00
8aab4e367f
[Feature] mm support prefix cache ( #4134 )
...
* 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 >
2025-10-27 17:39:51 +08:00
dc1a9c7287
perf: Optimize task queue communication from engine to worker ( #4531 )
...
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* 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 >
2025-10-25 22:45:38 +08:00
5a8c60454e
[BugFix] Fix decode_type which has been deleted in req and optimize token client retry scheme ( #4564 )
2025-10-23 05:08:10 -07:00
809c1ac7ec
feat: add post-processing step for pool_output ( #4462 )
...
* feat: add post-processing step for pool_output
* bugfix
* fix: test_serving_embedding
* fix test_request_to_batch_dicts
* fix: code style
2025-10-21 20:24:26 +08:00
ee915220bd
[Speculative Decoding] Add draft_logprobs Support for Speculative Decode MTP ( #4467 )
...
* feat: add draft_logprobs for Speculative Decode MTP
* feat: add draft_logprobs for Speculative Decode MTP
* feat: add draft_logprobs for Speculative Decode MTP
* fix: postprocess for speculative decode
* test: test_speculative_decoding_use_logprobs
* fix: test_completion_echo
* fix test_max_streaming_tokens
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-10-21 14:57:50 +08:00
670aaa3f83
[Bug fix] Fix pd for x1 thinking ( #4433 )
2025-10-16 12:03:45 +08:00
b4b579a7ed
Feature：Add support for Pooling Model Embedding and provide an OpenAI-compatible API. ( #4344 )
...
* feat: add OpenAIServing
* feat: add ZmqOpenAIServing & OpenAIServingEmbedding
* feat: Refine the basic ServingEngine class and introduce ServingContext
* fix: codestyle
* fix: request
* fix: pooling_params
* feat: _process_chat_template_kwargs
* feat: support batch request
* feat: pooling_params verify & default parameters
---------
Co-authored-by: sunlei1024 <sunlei1024@example.com >
2025-10-15 19:42:59 +08:00
kevin