Commit History

coreml: fix Whisper to CoreML conversion by disabling SDPA [no ci] (#2979)
bf862e4
unverified

danbev commited on

ci : add coreml job that converts base.en to coreml [no ci] (#2981)
26aba7a
unverified

danbev commited on

tests : re-enable tests [no ci] (#2977)
8c851e2
unverified

danbev commited on

android.java : re-add ggml source updates (#2975)
5dca9f3
unverified

danbev commited on

ci : re-enable freeBDS-latest job (#2973)
32bf9c9
unverified

danbev commited on

ci : re-enable android_java job (#2958)
e7fbecf
unverified

danbev commited on

android : add new ggml source files
69804b5

ggerganov commited on

ruby : add new ggml sources
c5a918e

ggerganov commited on

sync : ggml
db835f2

ggerganov commited on

SYCL: Remove misleading ggml_sycl_op_flatten function (llama/12387)
0a9c73a

Akarshan Biswas commited on

metal : use constexpr in FA kernels + fix typedef (llama/12659)
c699617

ggerganov commited on

musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (llama/12611)
12bb60d

R0CKSTAR commited on

cmake : fix ccache conflict (llama/12522)
22dfdf6

Jay commited on

cpu : rm unused variable (ggml/1166)
86eb3af

ngxson HF Staff commited on

cpu: de-duplicate some of the operators and refactor (ggml/1144)
09f2f18

cmdr2 commited on

cmake: improve Vulkan cooperative matrix support checks (#2966)
4be7f68
unverified

Sandro Hanea Sandro Hanea commited on

examples : update README links to point to pages deployment (#2971)
ba856a2
unverified

danbev commited on

ci : add github pages workflow for wasm examples (#2969)
7b99476
unverified

danbev commited on

feat: add health check endpoint to server (#2968)
cbeea6f
unverified

sachaarbonel commited on

whisper : remove unnecessary GGML_UNUSED macro (#2960)
b2e42a5
unverified

danbev commited on

sync : ggml
91362b9

ggerganov commited on

metal : improve FA + improve MoE (llama/12612)
04a3389

ggerganov commited on

vulkan: fix coopmat shader generation when cross-compiling (llama/12272)
7585c4a

Icenowy Zheng bandoti commited on

llamafile : ppc64le GEMV forwarding for FP32. (llama/12594)
1843f18

amritahs-ibm commited on

rpc : send hash when tensor data is above some fixed threshold (llama/12496)
c39f9c4

rgerganov commited on

opencl: add multi and vision rope, `gelu_quick` and `im2col` (llama/12600)
3261fcd

lhez commited on

bindings.go : add DetectedLanguage to go bindings (#2947)
1830e27
unverified

Amanda Der Bedrosian Amanda Der Bedrosian commited on

ruby : fix test failures in test_whisper (#2955)
2ccaffe
unverified

danbev commited on

examples : support progress_callback API for addon.node (#2941)
3f6a806
unverified

Lin Xiaodong linxiaodong commited on

xcf : fix visionOS build
2220ea9

ggerganov commited on

files : remove old wkv6 (#0)
ee92ae5

ggerganov commited on

sync : ggml
9745a6d

ggerganov commited on

ggml : sync/merge cmake,riscv,powerpc, add common.cmake (ggml/0)
f695cbf

ggerganov commited on

llamafile : ppc64le MMA implementation for Q4_0. (llama/12489)
d154905

amritahs-ibm commited on

SYCL: implement memset ggml backend buffer interface (llama/12580)
3f95f2b

Akarshan Biswas commited on

HIP: Add support for RDNA4 targets (llama/12372)
a73f01f

Slobodan Josic commited on

metal : refactor mat-vec code (llama/12569)
71d72f9

ggerganov commited on

ggml : fix MUL_MAT_ID repack with Q8_K (llama/12544)
a13f78c

ggerganov commited on

ggml-cpu : update KleidiAI to v1.5.0 (llama/12568)
9b4460a

Dan Johansson commited on

SYCL: disable Q4_0 reorder optimization (llama/12560)
33f8316

Akarshan Biswas commited on

opencl: simplify kernel embedding logic in cmakefile (llama/12503)
5f131ac

lhez Max Krasnyansky commited on

CUDA: Fix clang warnings (llama/12540)
efa6dac

R0CKSTAR commited on

vulkan: fix mul_mat_vec failure in backend tests (llama/12529)
09dd86a

jeffbolznv commited on

ggml : fix quantized cpy op (llama/12310)
608b377

ggerganov commited on

musa: refine compute capability (llama/12493)
5e508d2

R0CKSTAR commited on

vulkan: Optimize mul_mat_vec p021 and nc shaders (llama/12505)
6868981

jeffbolznv commited on

Vulkan: RTE rounding for cpy to quant (llama/12480)
8707beb

stduhpf jeffbolznv commited on

vulkan: workaround for AMD Windows driver 16 bit unpack8 bug (llama/12472)
417a5d6

Eve commited on

Fix build on Windows when ccache enabled (ggml/9954) (llama/9976)
bbd0292

蕭澧邦 Romain Biessy commited on

sycl: cleanup oneDNN related code (llama/12097)
959346b

Svetlozar Georgiev commited on