Spaces:
Sleeping
Sleeping
Commit History
metal : option to embed MSL source into compiled binary (#1842)
a46b62a
unverified
Didzis Gosko
commited on
metal : add im2col F32 dst support (llama/5132)
26aec77
unverified
SOTA 3-bit quants (llama/5196)
4649943
unverified
ggml : add max buffer sizes to opencl and metal backends (llama/5181)
3d354d0
unverified
slaren
commited on
metal : free metal objects (llama/5161)
ea7167a
unverified
Paul Tsochantaris
commited on
ci : fix yolo URLs + fix metal capture (ggml/712)
588f789
unverified
metal : add debug capture backend function (ggml/694)
ece88c3
unverified
ggml : add Vulkan backend (llama/2059)
5a97aba
unverified
metal : remove unused `n_buffers` and `buffers` (llama/5129)
a3e87d3
unverified
Paul Tsochantaris
commited on
metal : show compile log messages
ae08f31
unverified
metal : disable support for MUL_MAT F32 x F16
7fbc01f
unverified
ggml : sync ggml-metal.m
b4085c3
unverified
metal : create autorelease pool during library build (llama/4970)
9027276
unverified
metal : log `recommendedMaxWorkingSetSize` on iOS 16+ (llama/4936)
e2cc0e5
unverified
ggml : introduce GGML_CALL function annotation (llama/4850)
7815f68
unverified
metal : correctly set SIMD support flags on iOS (llama/4923)
1cf2fa9
unverified
metal : remove old API (llama/4919)
d6abb6a
unverified
metal : disable log for loaded kernels (llama/4794)
2305485
unverified
metal : refactor kernel loading code (llama/4794)
53e6bf8
unverified
llama : ggml-backend integration (llama/4766)
362430b
unverified
ggml : SOTA 2-bit quants (add IQ2_XS) (llama/4856)
5e827d5
unverified
metal : put encoder debug group behind a define (llama/4873)
6e822b8
unverified
Paul Tsochantaris
commited on
metal : fix deprecation warning (ggml/690)
b1e29bc
unverified
metal : wrap each operation in debug group (ggml/690)
b5e360f
unverified
Jack Mousseau
commited on
SOTA 2-bit quants (llama/4773)
75de5bf
unverified
metal : switch back to default.metallib (ggml/681)
b945a8f
unverified
ggml : add error handling to graph_compute (#1714)
92f24ee
unverified
metal : add kernel_get_rows_i32
459dd87
metal : optimize ggml_mul_mat_id (faster Mixtral PP) (llama/4725)
8bc6274
metal : enable shader debugging (cmake option) (llama/4705)
7dd37dc
sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)
aa86ade
unverified
sync : ggml (Metal fixes, new ops, tests) (#1633)
a0d4b48
unverified
metal : fix `ggml_metal_log` vargs (#1606)
b3cea90
unverified
metal : fix soft_max kernel src1 argument (#1602)
5692844
unverified
sync : ggml (new ops, new backend, etc) (#1602)
895e87a
unverified
metal : add backend function to check device family support (#1547)
c95e649
unverified
metal : fix build (#1544)
02dbf1a
unverified
sandrohanea
commited on
whisper : make large version explicit + fix data size units (#1493)
03a3210
unverified
ggml : fix some compile warnings
ad6c9c1
unverified
whisper : add full CUDA and Metal offloading (#1472)
da4acca
unverified
metal : fix asserts for setThreadgroupMemoryLength (close #1435)
b42b45f
unverified
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
7006035
unverified
metal : restore matrix x vector f16_f32 kerenls for now
2dd8c56
unverified
metal : add F32 support + update bench output
02d7878
unverified
whisper : Metal and ggml-alloc support (#1270)
714ee6b
unverified
sync : ggml (HBM + Metal + style) (#1264)
88deeba
unverified
ggml : posixify pagesize (#1251)
4902c26
unverified
Przemysław Pawełczyk
commited on