Ruben Ortlam 4317ddbe2b vulkan: add Flash Attention support for BFloat16 KV cache (llama/23420) ...

* vulkan: add flash attention bf16 kv support

* vulkan: bf16 FA coopmat1 support

* vulkan: bf16 FA coopmat2 support

* fix FA bf16 f32 fallback

* fix FA bf16 coopmat1 shader

* fix FA bf16 coopmat2 shader

* code cleanup

* cleanup comment change

* address feedback

* add O_TYPE for cm2 FA

* use O_TYPE for gqaStore function

* reduce BFLOAT16 ifdefs

2026-06-08 14:36:36 +03:00

..

ggml-blas

vulkan: add get/set tensor 2d functions (llama/22514)

2026-05-01 13:07:35 +03:00

ggml-cann

vulkan: add get/set tensor 2d functions (llama/22514)

2026-05-01 13:07:35 +03:00

ggml-cpu

model : support for DeepseekV32ForCausalLM with generic DeepSeek Sparse Attention (DSA) implementation (llama/23346)

2026-06-08 14:36:36 +03:00

ggml-cuda

CUDA: Check PTX version on host side to guard PDL dispatch (llama/23530)

2026-06-08 14:36:36 +03:00

ggml-hexagon

hexagon: basic/generic op fusion support and RMS_NORM+MUL fusion (llama/23835)

2026-05-29 09:47:30 +03:00

ggml-hip

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-metal

metal : add apple device id (llama/23566)

2026-05-29 09:47:30 +03:00

ggml-musa

…

ggml-opencl

opencl: move backend info printing into its own function (llama/23702)

2026-05-29 09:47:30 +03:00

ggml-openvino

openvino: driver setup, CI split, thread safety, and NPU optimizations (llama/21944)

2026-04-30 11:29:15 +03:00

ggml-rpc

rpc : keep last_graph_uid in the device context (llama/23273)

2026-05-25 12:26:07 +03:00

ggml-sycl

SYCL: implement ggml_sycl_pool_vmm (llama/22862)

2026-05-29 09:47:30 +03:00

ggml-virtgpu

ggml-virtgpu : include missing mutex header (llama/22810)

2026-05-14 21:26:48 +03:00

ggml-vulkan

vulkan: add Flash Attention support for BFloat16 KV cache (llama/23420)

2026-06-08 14:36:36 +03:00

ggml-webgpu

ggml-webgpu: Check earlier for WebGPU required features (llama/23879)

2026-06-08 14:36:36 +03:00

ggml-zdnn

vulkan: add get/set tensor 2d functions (llama/22514)

2026-05-01 13:07:35 +03:00

ggml-zendnn

ggml-zendnn : fixed naming of matmul function (llama/20964)

2026-05-29 09:47:30 +03:00

CMakeLists.txt

ggml : Parallelize quant LUT init (llama/23595)

2026-05-25 12:26:07 +03:00

ggml-alloc.c

ggml-alloc: fix out-of-bounds read in ggml_dyn_tallocr_remove_block (ggml/1492)

2026-05-25 12:26:07 +03:00

ggml-backend-dl.cpp

…

ggml-backend-dl.h

…

ggml-backend-impl.h

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-backend-meta.cpp

meta : Add missing buffer set in allreduce fallback !COMPUTE clear (llama/23480)

2026-05-29 09:47:30 +03:00

ggml-backend-reg.cpp

ggml : skip already registered backends and devices (llama/22296)

2026-04-30 11:29:21 +03:00

ggml-backend.cpp

ggml : Check the right iface method before using the fallback 2d get (llama/23514)

2026-05-25 12:26:07 +03:00

ggml-common.h

…

ggml-impl.h

ggml: add graph_reused (llama/21764)

2026-04-30 11:29:11 +03:00

ggml-opt.cpp

fix: free ctx_copy in ggml_opt_free to plug per-training-session leak (llama/21592)

2026-04-30 11:29:03 +03:00

ggml-quants.c

ggml : Parallelize quant LUT init (llama/23595)

2026-05-25 12:26:07 +03:00

ggml-quants.h

…

ggml-threading.cpp

…

ggml-threading.h

…

ggml.c

model : support for DeepseekV32ForCausalLM with generic DeepSeek Sparse Attention (DSA) implementation (llama/23346)

2026-06-08 14:36:36 +03:00

ggml.cpp

…

gguf.cpp

ggml: gguf_init_from_callback and gguf_init_from_buffer (llama/22341)

2026-05-25 12:44:04 +03:00