b10078

ggml-org/llama.cppb10078Jul 21, 2026by github-actions[bot]
AI Summary

Refactors Vulkan queue handling to use per-instance mutexes and unique handles, integrating VK_KHR_internally_synchronized_queues to bypass host-side locking when driver-side synchronization is supported.
Key Highlights

Vulkan queue refactor with per-instance mutexes
Integration of VK_KHR_internally_synchronized_queues
Improved thread safety and performance via driver-side synchronization
Use of unique_ptr for exclusive queue ownership
New Features

Vulkan internal synchronization optimization
Full Release Notes

<details open>

vulkan: Refactor vk_queue to use per-instance mutexes and unique handles (#23570)

* Refactor vk_queue to use per-instance mutexes and unique handles

* integrates VK_KHR_internally_synchronized_queues, abstracting the queue submission into a polymorphic interface that completely bypasses host-side mutex locking when driver-side synchronization is supported

* fix compilation error

* fix duplicate pNext chain for VkPhysicalDeviceInternallySynchronizedQueuesFeaturesKHR

* add fallback defines for VK_KHR_internally_synchronized_queues

* add null checks for queues in vk_device_struct destructor

* use unique_ptr for outer queues to enforce exclusive ownership and optimize lifetime

* use static constexpr for eInternallySynchronizedKHR

* add lock guard to ggml_vk_create_aliased_queue for thread safety

* initialize sync_query_features.internallySynchronizedQueues to VK_FALSE

* reuse sync_query_features for internallySynchronizedQueues and simplify chaining

* refactor internallySynchronizedQueues detection

* fix internallySynchronizedQueues query guard

* use eInternallySynchronizedKHR constant

* fix self-referential alias for eInternallySynchronizedKHR

* use macro for eInternallySynchronizedKHR fallback

* fix internallySynchronizedQueues query timing in ggml-vulkan.cpp to prevent device creation mismatch

* reset sync_query_features.pNext before reusing in device creation chain, also removed the redundant second probe call

* refactor internally synchronized queues detection to use chained feature query and avoid redundant API calls

* Update ggml/src/ggml-vulkan/ggml-vulkan.cpp

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* Update ggml/src/ggml-vulkan/ggml-vulkan.cpp

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* Update ggml/src/ggml-vulkan/ggml-vulkan.cpp

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* Update ggml/src/ggml-vulkan/ggml-vulkan.cpp

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* Update ggml/src/ggml-vulkan/ggml-vulkan.cpp

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* Update ggml/src/ggml-vulkan/ggml-vulkan.cpp

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* rename sync_enable_features to internally_synchronized_queues_features

* queue_flags is still computed before has_internally_synchronized_queues is set

* fix trailing whitespace

* replace eInternallySynchronizedKHR macro with static constexpr

* preserve source queue semantics in single-queue aliased transfer queue

* vulkan: fix cmd_pool access via pointer for compute_queue unique_ptr

* vulkan: lock queue during debug label emission when not internally synchronized

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

</details>

**Website:**
- <https://llama.app>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-macos-arm64.tar.gz)
- macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780)
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10078/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10078/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-bin-win-hip-radeon-x64.zip)

**openEuler:**
- [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705)
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

**UI:**
- [UI](https://github.com/ggml-org/llama.cpp/releases/download/b10078/llama-b10078-ui.tar.gz)