Commits

History for

Commits on Jun 2, 2024

Fix HIPBlas for Debian
daniandtheweb
committedJun 2, 2024
Update HIPBLAS CMake
daniandtheweb
committedJun 2, 2024

Commits on May 25, 2024

cmake : add Vulkan build (ggerganov#730 )
abetlen
committedMay 25, 2024

Commits on May 17, 2024

Add ggml rpc to cmake (ggerganov#827 )
abetlen
committedMay 17, 2024

Commits on Apr 3, 2024

cmake : add GGML_METAL_EMBED_LIBRARY (ggerganov#780 )
abetlen
committedApr 3, 2024

Commits on Mar 27, 2024

examples : fix CUBLAS leftovers (#0)
ggerganov
committedMar 27, 2024
sync : adapt to CUDA changes (#0)
ggerganov
committedMar 27, 2024

Commits on Mar 14, 2024

ggml : add ggml-common.h
ggerganov
committedMar 14, 2024

Commits on Feb 19, 2024

cmake : update CBLAS build flags (#0)
ggerganov
committedFeb 19, 2024

Commits on Jan 26, 2024

gpt-2 : clarify instructions for CLBlast on Android (ggerganov#706 )

luciferous
and
slaren
committedJan 26, 2024

Commits on Jan 6, 2024

fix ROCm on Windows (ggerganov#683 )

Cyberhan123
and
slaren
committedJan 6, 2024

Commits on Dec 27, 2023

cmake : update CUDA build to support VMM
ggerganov
committedDec 27, 2023

Commits on Dec 14, 2023

cmake : change installation path of static libraries to standard directory (ggerganov#645 )

davesjoewang
and
chengchiwang
committedDec 14, 2023

Commits on Dec 13, 2023

ggml: new gpu kernels + extends ggml_leaky_relu + ggml_pad (ggerganov#621 )

committedDec 13, 2023

Commits on Dec 5, 2023

ggml : full broadcast in mul, add, div + ggml_mul_mat_id, ggml_argsort, ggml_top_k (ggerganov#625 )

slaren
and
ggerganov
committedDec 5, 2023

Commits on Dec 1, 2023

cmake : add ROCm config (ggerganov#626 )
riverzhou
committedDec 1, 2023

Commits on Nov 17, 2023

sync : whisper.cpp (update whisper example + minor) (ggerganov#613 )
ggerganov
committedNov 17, 2023

Commits on Nov 3, 2023

sync : llama.cpp (CUDA opts, ggml-quants, YARN, etc.) (ggerganov#601 )
ggerganov
committedNov 3, 2023

Commits on Oct 30, 2023

ggml-backend v2 : add ggml_backend_sched (ggerganov#586 )

slaren
and
ggerganov
committedOct 30, 2023
cmake : cuda architectures: allow user override, only set local if not globally set (ggerganov#595 )
iboB
committedOct 30, 2023

Commits on Oct 6, 2023

ggml backends interface v1 (ggerganov#547 )

slaren
and
ggerganov
committedOct 6, 2023

Commits on Oct 4, 2023

cmake : add OPENCL_LIB to solve problem [cannot resolve external symbol clxxxx ] (ggerganov#527 )
wizardforcel
committedOct 4, 2023

Commits on Sep 8, 2023

cmake : solve prob "clblast.h not found" (ggerganov#506 )
wizardforcel
committedSep 8, 2023

Commits on Aug 29, 2023

CUDA: fix build and enable warnings (ggerganov#494 )
cebtenzzre
committedAug 29, 2023

Commits on Aug 28, 2023

cmake : enable some basic warnings globally (ggerganov#482 )

cebtenzzre
and
ggerganov
committedAug 28, 2023
cmake : fix MSVC build (ggerganov#479 )
cebtenzzre
committedAug 28, 2023
cmake : add WebAssembly check (ggerganov#487 )
ivanstepanovftw
committedAug 28, 2023

Commits on Aug 16, 2023

ggml : backport ggml-alloc from llama.cpp (ggerganov#433 )

smspillaz
and
slaren
committedAug 16, 2023

Commits on Aug 6, 2023

cmake : add avx compile options on Windows (synced from llama.cpp) (ggerganov#435 )
li-plus
committedAug 6, 2023

Commits on Aug 3, 2023

cmake : fix msvc cuda build - no need to specify stdlib (ggerganov#428 )
iboB
committedAug 3, 2023

Commits on Jul 23, 2023