llama.cpp/.github
Reese Levine 45cac7ca70
ggml-webgpu: fix compiler warnings and refactor FlashAttention encoding (#21052)
* Update workflows to remove dependence on llvmpipe

* Try setting Dawn_DIR

* remove c++20 initializers

* Move to proper guid

* Try avoiding segfaults on vulkan backend process exit

* Remove compiler warnings on parameter casting

* Fix soft_max and update reg_tile accumulation to f32 for better precision

* Refactor flash_attn a bit

* remove c++20 initializers and format

* Increase div precision for NVIDIA

* revert div precision and comment out ggml-ci node for now

* Formatting

* Try debugging on a failing CI node

* Revert "Try debugging on a failing CI node"

This reverts commit 1971e33cba.
2026-04-17 09:17:11 -07:00
..
actions ggml : add OpenVINO backend (#15307) 2026-03-14 07:56:55 +02:00
ISSUE_TEMPLATE issues: add openvino backends (#20932) 2026-03-24 14:41:10 +08:00
workflows ggml-webgpu: fix compiler warnings and refactor FlashAttention encoding (#21052) 2026-04-17 09:17:11 -07:00
labeler.yml ci: drop v5 all: composition from labeler.yml (#21627) 2026-04-09 08:20:19 +02:00
pull_request_template.md contrib: add "Requirements" section to PR template (#20841) 2026-03-23 16:59:02 +01:00