Skip to content

fix: RuntimeError in free_kv_cache with vLLM v1 (0.19+) #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
IthaloPS wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −4
Open

fix: RuntimeError in free_kv_cache with vLLM v1 (0.19+) #14

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions turboquant/integration/vllm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -472,7 +472,7 @@ def free_kv_cache(model_runner) -> int:
continue
attn_module = static_ctx[layer_name]
kv_list = getattr(attn_module, "kv_cache", None)
if kv_list and len(kv_list) > 0:
if kv_list is not None and len(kv_list) > 0:
ptrs_to_free.add(kv_list[0].data_ptr())

for layer_name, state in layer_states.items():
Expand All @@ -482,7 +482,7 @@ def free_kv_cache(model_runner) -> int:
continue
attn_module = static_ctx[layer_name]
kv_list = getattr(attn_module, "kv_cache", None)
if kv_list and len(kv_list) > 0:
if kv_list is not None and len(kv_list) > 0:
old = kv_list[0]
freed += old.nelement() * old.element_size()
kv_list[0] = tiny
Expand Down
4 changes: 2 additions & 2 deletions turboquant/vllm_attn_backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,7 +236,7 @@ def free_kv_cache(model_runner):
if attn_module is None:
continue
kv_list = getattr(attn_module, "kv_cache", None)
if kv_list and len(kv_list) > 0 and hasattr(kv_list[0], "data_ptr"):
if kv_list is not None and len(kv_list) > 0 and hasattr(kv_list[0], "data_ptr"):
ptrs_to_free.add(kv_list[0].data_ptr())

for layer_name, state in layer_states.items():
Expand All @@ -246,7 +246,7 @@ def free_kv_cache(model_runner):
if attn_module is None:
continue
kv_list = getattr(attn_module, "kv_cache", None)
if kv_list and len(kv_list) > 0:
if kv_list is not None and len(kv_list) > 0:
old = kv_list[0]
freed += old.nelement() * old.element_size()
kv_list[0] = tiny
Expand Down