Unverified Commit 15843047 authored by Wang Ran (汪然)'s avatar Wang Ran (汪然) Committed by GitHub
Browse files

Fix typos (#4368)

parent 8ec2ce07
...@@ -14,7 +14,7 @@ ...@@ -14,7 +14,7 @@
""" """
The entry point of inference server. (SRT = SGLang Runtime) The entry point of inference server. (SRT = SGLang Runtime)
This file implements HTTP APIs for the inferenc engine via fastapi. This file implements HTTP APIs for the inference engine via fastapi.
""" """
import asyncio import asyncio
......
...@@ -19,7 +19,7 @@ from sglang.srt.torch_memory_saver_adapter import TorchMemorySaverAdapter ...@@ -19,7 +19,7 @@ from sglang.srt.torch_memory_saver_adapter import TorchMemorySaverAdapter
Memory pool. Memory pool.
SGLang has two levels of memory pool. SGLang has two levels of memory pool.
ReqToTokenPool maps a a request to its token locations. ReqToTokenPool maps a request to its token locations.
TokenToKVPoolAllocator manages the indices to kv cache data. TokenToKVPoolAllocator manages the indices to kv cache data.
KVCache actually holds the physical kv cache. KVCache actually holds the physical kv cache.
""" """
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment