Skip to content

fix: rename op_offloat to op_offload in llama.py #2046

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
merged 1 commit into from
Aug 7, 2025
Merged

fix: rename op_offloat to op_offload in llama.py #2046

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
10 changes: 5 additions & 5 deletions llama_cpp/llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,7 @@ def __init__(
embedding: bool = False,
offload_kqv: bool = True,
flash_attn: bool = False,
op_offloat: Optional[bool] = None,
op_offload: Optional[bool] = None,
swa_full: Optional[bool] = None,
# Sampling Params
no_perf: bool = False,
Expand Down Expand Up @@ -174,7 +174,7 @@ def __init__(
embedding: Embedding mode only.
offload_kqv: Offload K, Q, V to GPU.
flash_attn: Use flash attention.
op_offloat: offload host tensor operations to device
op_offload: offload host tensor operations to device
swa_full: use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
no_perf: Measure performance timings.
last_n_tokens_size: Maximum number of tokens to keep in the last_n_tokens deque.
Expand Down Expand Up @@ -343,8 +343,8 @@ def __init__(
self.context_params.offload_kqv = offload_kqv
self.context_params.flash_attn = flash_attn

if op_offloat is not None:
self.context_params.op_offloat = op_offloat
if op_offload is not None:
self.context_params.op_offload = op_offload

if swa_full is not None:
self.context_params.swa_full = swa_full
Expand Down Expand Up @@ -2097,7 +2097,7 @@ def __getstate__(self):
embedding=self.context_params.embeddings,
offload_kqv=self.context_params.offload_kqv,
flash_attn=self.context_params.flash_attn,
op_offloat=self.context_params.op_offloat,
op_offload=self.context_params.op_offload,
swa_full=self.context_params.swa_full,
# Sampling Params
no_perf=self.context_params.no_perf,
Expand Down
Loading