Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)
Co-authored-by: SangBin Cho <rkooo567@gmail.com> Co-authored-by: dhou-xai <dhou@x.ai> Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
This commit is contained in:
@@ -34,11 +34,9 @@ class GlobalConfig:
|
||||
self.skip_special_tokens_in_output = True
|
||||
self.spaces_between_special_tokens_in_out = True
|
||||
|
||||
# Interpreter optimization configs
|
||||
# Language frontend interpreter optimization configs
|
||||
self.enable_precache_with_tracing = True
|
||||
self.enable_parallel_encoding = True
|
||||
|
||||
self.enable_flashinfer_mla = False
|
||||
|
||||
|
||||
global_config = GlobalConfig()
|
||||
|
||||
Reference in New Issue
Block a user