Skip to content

[codex] fix Metal custom V-cache set rows #34

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

Draft
lalalune wants to merge 1 commit into
base: feat/gemma4-assistant-arch
Choose a base branch
from
Draft

[codex] fix Metal custom V-cache set rows #34

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
11 changes: 10 additions & 1 deletion ggml/src/ggml-metal/ggml-metal-device.m
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1343,6 +1343,9 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
case GGML_TYPE_Q5_0:
case GGML_TYPE_Q5_1:
case GGML_TYPE_IQ4_NL:
case GGML_TYPE_TBQ3_0:
case GGML_TYPE_TBQ4_0:
case GGML_TYPE_Q4_POLAR:
case GGML_TYPE_I32:
return true;
default:
Expand Down Expand Up @@ -1370,6 +1373,9 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
case GGML_TYPE_Q5_0:
case GGML_TYPE_Q5_1:
case GGML_TYPE_Q8_0:
case GGML_TYPE_TBQ3_0:
case GGML_TYPE_TBQ4_0:
case GGML_TYPE_Q4_POLAR:
switch (op->type) {
case GGML_TYPE_F32:
case GGML_TYPE_F16:
Expand Down Expand Up @@ -1441,7 +1447,10 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
case GGML_TYPE_Q5_1:
case GGML_TYPE_IQ4_NL:
case GGML_TYPE_QJL1_256:
// // ELIZA-QJL-SET-ROWS-V1
case GGML_TYPE_TBQ3_0:
case GGML_TYPE_TBQ4_0:
case GGML_TYPE_Q4_POLAR:
// ELIZA-CUSTOM-KV-SET-ROWS-V1
return true;
default:
return false;
Expand Down
Loading
Loading