ci : more platforms coverage (#1101)
c4448fa
unverified
alonfaraj
Alon Faraj
commited on
Spaces:
Running
Running
Commit History
Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)"
1e5ddb0
unverified
ggml : sync latest repo (mostly refactoring changes)
d97fd69
unverified
ggml : do not use _GNU_SOURCE gratuitously (#1027)
3a69cdf
unverified
Przemysław Pawełczyk
commited on
ggml : sync latest ggml lib
a100c9a
unverified
ggml : update WASM SIMD
84c1cc7
unverified
ggml : sync latest ggml repo
6ee8740
unverified
ggml : add AVX dot products
7e7b11c
unverified
ggml : sync latest ggml
803e1be
unverified
ggml : fix 32-bit ARM build + quantization
87ee234
ggml : sync ggml (clBLAST + tensor names)
f50d3b3
unverified
ggml : fix UB (int << 31)
8253b98
unverified
whisper : add integer quantization support (#540)
a5f8f3c
unverified
ggml : fix WASM build
c3d7603
unverified
ggml : fix 32-bit ARM NEON (#836)
5fa72ca
unverified
ggml : use vzip instead of vuzp for consistency
741db99
unverified
ggml : fix WASM build
ada8c2d
unverified
ggml : sync with ggml repo (warning fixes + asserts)
caf2759
unverified
ggml : sync latest ggml + llama.cpp updates (quantization)
ede1268
unverified
ggml, ci : fix build on whisper.android (ARM_NEON) + add CI (#764)
dedf05b
unverified
ggml : sync latest ggml
7b8292f
unverified
ggml : fix q4_1 dot product types (#759)
984a856
unverified
ggml : sync latest changes from ggml and llama.cpp
3bd52ce
unverified
ggml : fix WASM build
70332a0
unverified
ggml : backport llama.cpp updates (close #709)
bf6b4f8
unverified
talk-llama : add new example + sync ggml from llama.cpp (#664)
a8c74e6
unverified
whisper : reduce memory usage during inference (#431)
3aa9e6c
unverified
whisper : PPC64 big-endian support (#398)
239569b
unverified
fitzsim
commited on
bench : add memcpy and ggml_mul_mat benchmarks
a660ed9
unverified
ggml : remove obsolete zeroing + comment fixes (#390)
9c35c0d
unverified
ggml : correct behaviour of ggml_vec_sum_f32 (#390)
ffffc6e
unverified
Abitofevrything
commited on
ggml : improve vec_dot_f16 unrolling in flash_attn_f16
6e57274
unverified
ggml : fix bug in new soft max computation
c59ce76
unverified
ggml : when using BLAS start only 1 CPU thread
6c4692f
unverified
ggml : fix running tasks with variable number of threads
2078d85
unverified
ggml : unroll ggml_vec_dot_f16 in ggml_compute_forward_flash_attn_f16
f07fecd
unverified
whisper : revert accidental MB change
db991e1
unverified
ggml : speed-up soft max via Accelerate + unroll
fdaf59a
unverified
ggml : use vDSP_sve and vDSP_maxv from Accelerate
ed14a8b
unverified
ggml : make gcc happy (minor)
496acd2
unverified
ggml : add SSE3 and fp16 conversion lookup table (#368)
2c3f7d4
unverified
whisper : document POWER VSX support
4dbf7ee
Thomas Fitzsimmons
commited on
ggml : reorganize POWER9 ppc64le SIMD code
e0a5614
Thomas Fitzsimmons
commited on
ggml : change f16 load and store macro arguments
4a68b87
Thomas Fitzsimmons
commited on
ggml : add void to argument-less functions
f06f912
unverified
ggml : define MIN / MAX only if not defined (minor)
2117da6
unverified
ggml : improve f16 acceleration for POWER9 ppc64le
f92a260
Thomas Fitzsimmons
commited on