Releases: allozaur/llama.cpp
Releases · allozaur/llama.cpp
b6344
Vulkan: Add Integer Dot Product mul_mat_vec shader for legacy quants …
b6341
CUDA: fix build error from ambiguous __half conversions in conv2d (#1…
b6259
CUDA: fix half2 -> half conversion for HIP (#15529)
b6209
opencl: mark `argsort` unsupported if cols exceed workgroup limit (#1…
b6160
server : add SWA checkpoints (#15293) * server : add SWA checkpoints ggml-ci * cont : server clean-up * server : handle state restore fails * llama : add extended llama_state_seq_ API * server : do not make checkpoints if --swa-full ggml-ci * llama : remove flags value for NONE * server : configure number of SWA checkpoints with CLI arg ggml-ci * args : fix scope of new argument
b6075
opencl: fix adreno compiler detection logic (#15029)
b6059
vendor : update vendored copy of google/minja (#15011) * vendor : update vendored copy of google/minja Signed-off-by: Lennart Austenfeld <[email protected]> * Re-remove trailing whitespace Signed-off-by: Lennart Austenfeld <[email protected]> * Remove another trailing whitespace Signed-off-by: Lennart Austenfeld <[email protected]> --------- Signed-off-by: Lennart Austenfeld <[email protected]>
b6027
HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only …
b6026
HIP: add GGML_HIP_MMQ_MFMA option to allow disableing the MFMA path. …