Skip to content

fix(llama): release a vision chat handler's mtmd context on close (#2342) #2343

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

Merged
abetlen merged 2 commits into from
Aug 17, 2026
+3 −5
Merged

fix(llama): release a vision chat handler's mtmd context on close (#2342) #2343

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5090bff
fix(llama): release a vision chat handler's mtmd context on close (#2…
Jul 17, 2026
11aeacd
fix: bind multimodal context cleanup to model
abetlen Aug 17, 2026
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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- fix(example): retain recurrent state for server MTP rollback
- feat: update llama.cpp to ggml-org/llama.cpp@adb55e514
- fix(server): show falsey defaults in CLI help by @cupkk in #2355
- fix: release multimodal contexts when closing Llama by @Anai-Guo in #2343

## [0.3.34]

Expand Down
7 changes: 2 additions & 5 deletions llama_cpp/llama_chat_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@
import string

from datetime import datetime
from contextlib import ExitStack
from typing import (
Any,
Dict,
Expand Down Expand Up @@ -2779,7 +2778,6 @@ def __init__(self, clip_model_path: str, verbose: bool = True):
self.clip_model_path = clip_model_path
self.verbose = verbose
self._mtmd_cpp = mtmd_cpp
self._exit_stack = ExitStack()
self.mtmd_ctx: Optional[mtmd_cpp.mtmd_context_p] = None

if not os.path.exists(clip_model_path):
Expand Down Expand Up @@ -2825,7 +2823,7 @@ def mtmd_free():
self._mtmd_cpp.mtmd_free(self.mtmd_ctx)
self.mtmd_ctx = None

self._exit_stack.callback(mtmd_free)
llama_model._stack.callback(mtmd_free)

def load_image(self, image_url: str) -> bytes:
return self._load_image(image_url)
Expand Down Expand Up @@ -3278,7 +3276,6 @@ def __init__(
self.verbose = verbose
self.use_gpu = use_gpu
self._mtmd_cpp = mtmd_cpp
self._exit_stack = ExitStack()
self.mtmd_ctx: Optional[mtmd_cpp.mtmd_context_p] = None

if not os.path.exists(clip_model_path):
Expand Down Expand Up @@ -3321,7 +3318,7 @@ def mtmd_free():
self._mtmd_cpp.mtmd_free(self.mtmd_ctx)
self.mtmd_ctx = None

self._exit_stack.callback(mtmd_free)
llama_model._stack.callback(mtmd_free)

def load_image(self, image_url: str) -> bytes:
return self._load_image(image_url)
Expand Down