lhezandGitHub 3a6db741a8 opencl: refactor backend initilization (#23318) ...

* opencl: refactor initialization

* opencl: refactor GPU identification

* opencl: rename for consistency

* opencl: cache global mem size in dev_ctx

* opencl: adjust log level

* opencl: load argsort and flash_attn kernels in supports_op

* argsort kernel must be built for supports_op for querying the max
  workgroups
* flash_attn kernel has many variants, only load them when needed

2026-05-20 09:57:36 -07:00

..

cmake

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

include

llama + spec: MTP Support (#22673)

2026-05-16 20:06:23 +08:00

src

opencl: refactor backend initilization (#23318)

2026-05-20 09:57:36 -07:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : bump version to 0.12.0 (ggml/1494)

2026-05-16 16:11:29 +03:00