mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[Feature] [KVCache] support attention_store kv cache backend (#5823)
* [feat] support attention_store kv cache backend * [fix] fix codestyle * [chore] optimize log * [fix] fix write storage task * [fix] fix read storage * [fix] fix code conflict after merge develop * [fix] fix cache bytes and read task token ids * [chore] add model for cache transfer manager * [chore] add some log * [chore] remove launched_cache_manager_signal * [fix] fix write_back_storage_task match_block_num condition * [fix] fix swap_cost_time * [ci] fix ci * Update fastdeploy/engine/sched/resource_manager_v1.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update fastdeploy/cache_manager/cache_transfer_manager.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update fastdeploy/cache_manager/transfer_factory/mooncake_store/attention_store.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
@@ -181,10 +181,6 @@ class LLMEngine:
|
||||
device_ids = self.cfg.parallel_config.device_ids.split(",")
|
||||
self.cache_manager_processes = self.engine.start_cache_service(device_ids, self.ipc_signal_suffix)
|
||||
|
||||
# Launch components: scheduler, cache_manager, expert_service et.al.
|
||||
if self.cfg.scheduler_config.splitwise_role != "mixed":
|
||||
self.launched_cache_manager_signal.value[0] = 1
|
||||
|
||||
if self.cfg.scheduler_config.splitwise_role != "mixed" and envs.FD_ENABLE_INTERNAL_ADAPTER:
|
||||
envs.FD_ZMQ_RECV_REQUEST_SERVER_PORT = envs.FD_ZMQ_RECV_REQUEST_SERVER_PORTS.split(",")[0]
|
||||
envs.FD_ZMQ_SEND_RESPONSE_SERVER_PORT = envs.FD_ZMQ_SEND_RESPONSE_SERVER_PORTS.split(",")[0]
|
||||
|
||||
Reference in New Issue
Block a user