vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 15:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

slove [Bug] #1023

Browse source 
Only modified the mixed single and double quotes in server/config/config.py
This commit is contained in:
Qin's repo 2025-04-03 14:37:32 +08:00 • committed by GitHub
parent 72e8e16fa4
commit 2c3a3a1e1c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 10 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

20
ktransformers/server/config/config.py
View file

@ -184,18 +184,18 @@ class Config(metaclass=Singleton):
self.prompt_file = self.local_chat_config.get("prompt_file", None)
# asyncserver
self.sched_strategy = cfg['async_server']['sched_strategy']
self.sched_port = cfg['async_server']['sched_port']
self.sched_metrics_port = cfg['async_server']['sched_metrics_port']
self.kvc2_metrics_port = cfg['async_server']['kvc2_metrics_port']
self.max_batch_size = cfg['async_server']['max_batch_size']
self.page_size = cfg['attn']['page_size']
self.chunk_size = cfg['attn']['chunk_size']
self.memory_gpu_only = cfg['kvc2']['gpu_only']
self.sched_strategy = cfg["async_server"]["sched_strategy"]
self.sched_port = cfg["async_server"]["sched_port"]
self.sched_metrics_port = cfg["async_server"]["sched_metrics_port"]
self.kvc2_metrics_port = cfg["async_server"]["kvc2_metrics_port"]
self.max_batch_size = cfg["async_server"]["max_batch_size"]
self.page_size = cfg["attn"]["page_size"]
self.chunk_size = cfg["attn"]["chunk_size"]
self.memory_gpu_only = cfg["kvc2"]["gpu_only"]
self.cache_lens = ((self.cache_lens + self.page_size - 1) // self.page_size) * self.page_size
self.gpu_memory_size = 2*576*61*self.cache_lens
self.utilization_percentage = 1.0 #cfg['kvc2']['utilization_percentage']
self.cpu_memory_size_GB = cfg['kvc2']['cpu_memory_size_GB']
self.utilization_percentage = 1.0 #cfg["kvc2"]["utilization_percentage"]
self.cpu_memory_size_GB = cfg["kvc2"]["cpu_memory_size_GB"]
# only support 2 prefill task
self.max_prefill_batch_size = 2
self.max_decode_batch_size = self.max_batch_size - self.max_prefill_batch_size