 swittk
|
1b0fd45465
ggml : Allow usage of CLBlast alongside Accelerate.framework (#1336)
|
2 years ago |
 Ron Jailall
|
20fbf2a2a0
ggml : change immintrin.h to intrin.h for compatibility (#1307)
|
2 years ago |
 Georgi Gerganov
|
799fdc1b5d
ggml : vectorize Q8_0 quantization
|
2 years ago |
|
Georgi Gerganov
|
5d5817ca60
ggml : fix 32-bit ARM
|
2 years ago |
 Marvin Gießing
|
cc0bb7235c
ggml : fix ppc64le build error and make cmake detect Power processors (#1284)
|
2 years ago |
 slaren
|
2d099e5193
ggml: add names to tensors (#1268)
|
2 years ago |
 slaren
|
58b367c2d7
cuBLAS: refactor and optimize f16 mat mul performance (#1259)
|
2 years ago |
 Kerfuffle
|
2bdc09646d
ggml : fix ggml_used_mem() (#1264)
|
2 years ago |
|
Georgi Gerganov
|
7ff0dcd320
ggml : fix UB (int << 31)
|
2 years ago |
|
Georgi Gerganov
|
6bc4400e67
ggml : add Q5 WASM SIMD + GGML_FTYPE
|
2 years ago |
|
Georgi Gerganov
|
3e5aa8a1c4
ggml : fix labels for GGML_OP_ALIBI
|
2 years ago |
|
Georgi Gerganov
|
c3ca7a5f05
ggml : fix 32-bit ARM NEON
|
2 years ago |
|
Georgi Gerganov
|
e8c051611a
ggml : use vzip instead of vuzp for consistency
|
2 years ago |
|
Georgi Gerganov
|
0b5a935099
ggml : fix visibility and unused warnings
|
2 years ago |
|
Georgi Gerganov
|
ec728e44d7
ggml : fix #if for f32_f32 mul_mat (CLBlast) (#1229)
|
2 years ago |
|
Georgi Gerganov
|
214b6a3570
ggml : adjust mul_mat_f16 work memory (#1226)
|
2 years ago |
|
slaren
|
7fc50c051a
cuBLAS: use host pinned memory and dequantize while copying (#1207)
|
2 years ago |
 Henri Vasserman
|
b1ee8f59b4
cuBLAS: non-contiguous tensor support (#1215)
|
2 years ago |
 Stephan Walter
|
36d19a603b
Remove Q4_3 which is no better than Q5 (#1218)
|
2 years ago |
|
Georgi Gerganov
|
55390bcaf2
ggml : sync ggml (ggml_alibi)
|
2 years ago |
|
Georgi Gerganov
|
11d902364b
ggml : add helper debug printf in soft_max
|
2 years ago |
 0cc4m
|
7296c961d9
ggml : add CLBlast support (#1164)
|
2 years ago |
 Yann Follet
|
04aaae1d79
add avx2 for dot_q8_0_q8_0, 2x faster than scalar (#1211)
|
2 years ago |
|
Stephan Walter
|
0b2da20538
ggml : slightly faster AVX2 implementation for Q5 (#1197)
|
2 years ago |
|
Georgi Gerganov
|
574406dc7e
ggml : add Q5_0 and Q5_1 quantization (#1187)
|
2 years ago |
|
Georgi Gerganov
|
7a32fcb3b2
ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)
|
2 years ago |
 unbounded
|
dd0eabc049
ggml : use full range for Q4_0 and Q4_2 quantization (#729)
|
2 years ago |
 xaedes
|
54bb60e268
ggml : fix bug in ggml_compute_forward_sum_f32 (#1162)
|
2 years ago |
|
Stephan Walter
|
2ec83428de
Fix build for gcc 8 and test in CI (#1154)
|
2 years ago |
|
Georgi Gerganov
|
ec9cdb6752
ggml : do not print perf ops that have not been used at all
|
2 years ago |
