 compilade
|
f44f793172
ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (#15379)
|
5 months ago |
|
compilade
|
e54d41befc
gguf-py : add Numpy MXFP4 de/quantization support (#15111)
|
6 months ago |
 Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
6 months ago |
 Daniel Bevenius
|
497be7c01d
ggml-quants : rename best_mad to best_error (ggml/1283)
|
7 months ago |
 xctan
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
8 months ago |
|
Daniel Bevenius
|
13b0a04597
whisper: remove MSVC warnings pragmas (whisper/3090)
|
9 months ago |
 mgroeber9110
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
11 months ago |
 Djip007
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
 Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
 Eve
|
3407364776
Q6_K AVX improvements (#10118)
|
1 year ago |
 snadampal
|
6a066b9978
fix build break on arm64 linux (#10166)
|
1 year ago |
 Dan Johansson
|
6a0f779484
ggml : add run-time detection of neon, i8mm and sve (#9331)
|
1 year ago |
|
slaren
|
23e0d70bac
ggml : move common CPU backend impl to new header (#9509)
|
1 year ago |
|
Eve
|
5c3d0f1824
ggml : IQ4_NL sgemm + Q4_0 AVX optimization (#9422)
|
1 year ago |
 Prashant Vithule
|
5fac4d5764
ggml : vector length agnostic SVE support (#9290)
|
1 year ago |
|
compilade
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 year ago |
|
Georgi Gerganov
|
231cff5f6f
sync : ggml
|
1 year ago |
 jdomke
|
76614f352e
ggml : reading the runtime sve config of the cpu (#8709)
|
1 year ago |
 CarterLi999
|
75af08c475
ggml: bugfix: fix the inactive elements is agnostic for risc-v vector (#8748)
|
1 year ago |
|
Georgi Gerganov
|
345c8c0c87
ggml : add missing semicolon (#0)
|
1 year ago |
 Mahesh Madhav
|
a05ca93697
ggml : loop tiling optimizations for scalar path (ggml/898)
|
1 year ago |
|
slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
1 year ago |
 Mark Zhuang
|
04bab6b7da
ggml: fix compile error for RISC-V (#8623)
|
1 year ago |
|
slaren
|
87e397d00b
ggml : fix quant dot product with odd number of blocks (#8549)
|
1 year ago |
|
Georgi Gerganov
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 year ago |
 Dibakar Gope
|
0f1a39f343
ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)
|
1 year ago |
|
Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
