Bugfix: LMCache Connector with Sglang (#12946)
Signed-off-by: Mohd Muzzammil <me.muzzammil@samsung.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
gemini-code-assist[bot]
parent
61c7fe7aed
commit
1f2a6c691b
@@ -107,7 +107,7 @@ class LMCRadixCache(RadixCache):
|
|||||||
"v_buffer",
|
"v_buffer",
|
||||||
getattr(self.token_to_kv_pool_allocator._kvcache, "v_buffer"),
|
getattr(self.token_to_kv_pool_allocator._kvcache, "v_buffer"),
|
||||||
),
|
),
|
||||||
tp_group=tp_group,
|
tp_group=tp_group.device_group if tp_group is not None else None,
|
||||||
)
|
)
|
||||||
|
|
||||||
self.load_stream = torch.cuda.Stream()
|
self.load_stream = torch.cuda.Stream()
|
||||||
|
|||||||
Reference in New Issue
Block a user