 Alberto Cabrera Pérez
|
cd8370b408
ggml-cpu: aarm64: q4_K repack gemm and gemv implementations (dotprod only) (#17494)
|
2 月之前 |
|
Alberto Cabrera Pérez
|
5449367b21
Fix chunks being too small with small matrix sizes (#17526)
|
2 月之前 |
|
Alberto Cabrera Pérez
|
dbb852b549
ggml-cpu: arm64: q4_K repack gemm and gemv implementations (i8mm) (#16739)
|
2 月之前 |
 Alberto Cabrera Pérez
|
becc4816dd
ggml-cpu: handle 3d tensors in repack mat_mul (#17241)
|
2 月之前 |
 Georgi Gerganov
|
2776db6c81
Revert "ggml-cpu: handle 3d tensors in repack mat_mul (#17030)" (#17233)
|
2 月之前 |
|
Alberto Cabrera Pérez
|
1c398dc9ec
ggml-cpu: handle 3d tensors in repack mat_mul (#17030)
|
2 月之前 |
 Noah
|
1f5accb8d0
Fix garbled output with REPACK at high thread counts (#16956)
|
2 月之前 |
 Max Krasnyansky
|
517b7170e1
cpu: introduce chunking for repack matmuls and enable matmul-id chunking on ARM64 (#16833)
|
3 月之前 |
|
Georgi Gerganov
|
00f35d509e
ggml : repack block_iq4_nlx8 (#14904)
|
5 月之前 |
 Srihari-mcw
|
baad94885d
ggml : Q2k interleaving implementation - x86/x64 SIMD (#14373)
|
6 月之前 |
 Daniel Bevenius
|
5592f278b6
ggml-cpu : remove stdlib include from repack.cpp (ggml/1276)
|
6 月之前 |
 Aaron Teo
|
60ef23d6c1
ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
|
7 月之前 |
 Christian Kastner
|
6369be0735
Implement GGML_CPU_ALL_VARIANTS for PowerPC (#14286)
|
7 月之前 |
|
Georgi Gerganov
|
d27b3ca175
ggml : fix repack work size for mul_mat_id (#14292)
|
7 月之前 |
 xctan
|
860a9e4eef
ggml-cpu : remove the weak alias trick (#14221)
|
7 月之前 |
|
xctan
|
3555b3004b
ggml-cpu : rework weak alias on apple targets (#14146)
|
7 月之前 |
 xctan
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
7 月之前 |
