Skip to content

Conversation

JohannesGaessler
Copy link
Collaborator

Out of habit from llama-bench I'm trying to set FlashAttention via e.g. -fa 0. This PR adds numeric aliases for on/off/auto.

common/arg.cpp Outdated
string_format("set Flash Attention use ('on', 'off', or 'auto', default: '%s')", llama_flash_attn_type_name(params.flash_attn_type)),
[](common_params & params, const std::string & value) {
if (value == "on" || value == "enabled") {
if (value == "on" || value == "enabled" || "1") {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if (value == "on" || value == "enabled" || "1") {
if (value == "on" || value == "enabled" || value == "1") {

Same for the rest.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you.

@JohannesGaessler JohannesGaessler merged commit c466abe into ggml-org:master Sep 2, 2025
48 checks passed
walidbr pushed a commit to walidbr/llama.cpp that referenced this pull request Sep 7, 2025
Nexesenex added a commit to Nexesenex/croco.cpp that referenced this pull request Oct 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants