8000 vulkan: Enable VK_KHR_cooperative_matrix extension for Intel Xe2 GPUs by rillomas · Pull Request #14001 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

vulkan: Enable VK_KHR_cooperative_matrix extension for Intel Xe2 GPUs #14001

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 7 commits into from
Jun 5, 2025
Merged

vulkan: Enable VK_KHR_cooperative_matrix extension for Intel Xe2 GPUs #14001

Changes from 1 commit 8000
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
981282a
allowing B580 and U9-288V
rillomas May 27, 2025
4a4b0bf
experimenting code to detect Xe2
rillomas May 28, 2025
67aca56
allowing coopmat only for Xe2 GPUs
rillomas May 29, 2025
b517286
fixed comment wording
rillomas May 29, 2025
8f1b1f9
fixed comment wording
rillomas Jun 2, 2025
a0dd779
Merge remote-tracking branch 'origin/master' into allow-list-intel-co…
rillomas Jun 4, 2025
57c58b3
removed unnecessary driver check
rillomas Jun 5, 2025
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
Prev Previous commit
8000
removed unnecessary driver check
  • Loading branch information
@rillomas
rillomas committed Jun 5, 2025
commit 57c58b346b85339efdd55d30ab35d06d3a53007a
9 changes: 3 additions & 6 deletions ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10199,12 +10199,9 @@ static bool ggml_vk_instance_portability_enumeration_ext_available(const std::ve
static bool ggml_vk_khr_cooperative_matrix_support(const vk::PhysicalDeviceProperties& props, const vk::PhysicalDeviceDriverProperties& driver_props, vk_device_architecture arch) {
switch (props.vendorID) {
case VK_VENDOR_ID_INTEL:
if (driver_props.driverID == vk::DriverId::eIntelProprietaryWindows || driver_props.driverID == vk::DriverId::eIntelOpenSourceMESA) {
// Only allowing Xe2 GPU at the moment since Xe2 GPU can gain significant performance boost,
// while some older hardware (ex. Arc A770) has performance regressions
return arch == vk_device_architecture::INTEL_XE2;
}
return false;
// Only allowing Xe2 GPU at the moment since Xe2 GPU can gain significant performance boost,
// while some older hardware (ex. Arc A770) has performance regressions
return arch == vk_device_architecture::INTEL_XE2;
case VK_VENDOR_ID_AMD:
if (driver_props.driverID == vk::DriverId::eAmdProprietary || driver_props.driverID == vk::DriverId::eAmdOpenSource) {
// Workaround for AMD proprietary driver reporting support on all GPUs
Expand Down
Loading
0