EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Fix typos in infer_batch.py (#354)

Browse Source
This commit is contained in:
Tom Dörr
2024-04-09 09:10:05 +02:00
committed by GitHub
parent ff99c38a07
commit 550a4f78f3
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/srt/managers/router/infer_batch.py
View File

@@ -240,7 +240,7 @@ class Batch:
out_cache_loc = self.token_to_kv_pool.alloc(extend_num_tokens) out_cache_loc = self.token_to_kv_pool.alloc(extend_num_tokens)
if out_cache_loc is None: if out_cache_loc is None:
print("Prefill out of memory. This should nerver happen.") print("Prefill out of memory. This should never happen.")
self.tree_cache.pretty_print() self.tree_cache.pretty_print()
exit() exit()
@@ -402,7 +402,7 @@ class Batch:
self.out_cache_loc = self.token_to_kv_pool.alloc(bs) self.out_cache_loc = self.token_to_kv_pool.alloc(bs)
if self.out_cache_loc is None: if self.out_cache_loc is None:
print("Decode out of memory. This should nerver happen.") print("Decode out of memory. This should never happen.")
self.tree_cache.pretty_print() self.tree_cache.pretty_print()
exit() exit()