Georgi Gerganov
|
6d1616944d
ggml : prevent builds with -ffinite-math-only (#7726)
|
1 ano atrás |
Masaya, Kato
|
a5735e4426
ggml : use OpenMP as a thread pool (#7606)
|
1 ano atrás |
Georgi Gerganov
|
0c27e6f62e
ggml : fix loongson compile warnings (#7537)
|
1 ano atrás |
Chris Elrod
|
59b0d07766
faster avx512 exp implementation (#7551)
|
1 ano atrás |
junchao-loongson
|
d5c05821f3
ggml : fix loongarch build (O2 issue) (#7636)
|
1 ano atrás |
Georgi Gerganov
|
fb76ec31a9
ggml : fix YARN + add tests + add asserts (#7617)
|
1 ano atrás |
Radoslav Gerganov
|
210d99173d
llama-bench : add support for the RPC backend (#7435)
|
1 ano atrás |
slaren
|
87bdf2a199
ggml : use atomic_flag for critical section (#7598)
|
1 ano atrás |
Georgi Gerganov
|
72de268bec
ggml : restore ggml_rope_xpos_inplace (ggml/0)
|
1 ano atrás |
zhouwg
|
504f0c340f
ggml : fix typo in ggml.c (#7603)
|
1 ano atrás |
Georgi Gerganov
|
0548a4187f
ggml : generalize GGML_OP_CONCAT (#7563)
|
1 ano atrás |
Masaya, Kato
|
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
|
1 ano atrás |
Georgi Gerganov
|
d48c88cbd5
ggml : remove ggml_flash_attn and ggml_flash_ff (#7463)
|
1 ano atrás |
Georgi Gerganov
|
e84b71c2c6
ggml : drop support for QK_K=64 (#7473)
|
1 ano atrás |
Georgi Gerganov
|
3e5faa8503
cuda : fix rope + add tests (#7452)
|
1 ano atrás |
liuwei-git
|
201cc11afa
llama : add phi3 128K model support (#7225)
|
1 ano atrás |
junchao-loongson
|
65c58207ec
ggml : add loongarch lsx and lasx support (#6454)
|
1 ano atrás |
Srihari-mcw
|
33c8d50acc
Add provisions for windows support for BF16 code including CMake provision for enabling AVX512_BF16 (#7258)
|
1 ano atrás |
Johannes Gäßler
|
5ca49cbecd
ggml: implement quantized KV cache for FA (#7372)
|
1 ano atrás |
Georgi Gerganov
|
511182eabb
android : use "ci-android" branch for CI (#7341)
|
1 ano atrás |
Justine Tunney
|
934266c0e0
ggml : rewrite silu and softmax for cpu (#7154)
|
1 ano atrás |
kunnis
|
e1b40ac3b9
ggml : use dynamic thread scheduling for matrix multiplication (#6915)
|
1 ano atrás |
slaren
|
344f9126cc
ggml : tag ggml_tensor::backend as deprecated (#7290)
|
1 ano atrás |
John Balis
|
48aa8fd1f2
ggml : add `ggml_upscale_ext` (ggml/814)
|
1 ano atrás |
Georgi Gerganov
|
e8a7fd4fb0
metal : support FA without mask + add asserts (#7278)
|
1 ano atrás |
Georgi Gerganov
|
c3c88f296a
ggml : try fix ppc64 (whisper/0)
|
1 ano atrás |
Georgi Gerganov
|
325756d28d
ggml : resolve merge (ggml/0)
|
1 ano atrás |
Justina Cho
|
f5ef34e428
feat: implemented sigmoid function (ggml/806)
|
1 ano atrás |
Georgi Gerganov
|
9cb317f77e
ggml : full ALiBi support (#7192)
|
1 ano atrás |
Justine Tunney
|
3855416027
ggml : introduce bfloat16 support (#6412)
|
1 ano atrás |