scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-11 22:51:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 123

Remove duplicate MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB definition

Browse source
This commit is contained in:
Mukesh Kumar Shah 2026-04-06 18:06:23 +05:30
parent 0df2b0d096
commit a5aa9392ae
1 changed files with 0 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
litellm/constants.py
View file

@ -388,9 +388,6 @@ CACHED_STREAMING_CHUNK_DELAY = float(os.getenv("CACHED_STREAMING_CHUNK_DELAY", 0
AUDIO_SPEECH_CHUNK_SIZE = int(
os.getenv("AUDIO_SPEECH_CHUNK_SIZE", 8192)
) # chunk_size for audio speech streaming. Balance between latency and memory usage
MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB = int(
os.getenv("MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB", 512)
)
DEFAULT_MAX_TOKENS_FOR_TRITON = int(os.getenv("DEFAULT_MAX_TOKENS_FOR_TRITON", 2000))
#### Networking settings ####
request_timeout: float = float(os.getenv("REQUEST_TIMEOUT", 6000)) # time in seconds