 shalinib-ibm
|
3a0d10533a
Q4/Q8 Tiled Gemm Optimization. (#16999)
|
2 months ago |
|
shalinib-ibm
|
a6a58d6478
llamafile: PowerPC Sgemm Optimization (#15558)
|
5 months ago |
|
shalinib-ibm
|
55c509daf5
ggml : refactor llamafile_sgemm PPC code (#14673)
|
7 months ago |
 Aaron Teo
|
60ef23d6c1
ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
|
7 months ago |
|
Aaron Teo
|
faed5a5f5d
llamafile : support s390x SIMD instruction set (#14273)
|
7 months ago |
 Diego Devesa
|
6adc3c3ebc
llama : add thread safety test (#14035)
|
7 months ago |
|
shalinib-ibm
|
3f3769ba76
ggml : Enable MMA for BF16 in llamafile_sgemm (#13148)
|
9 months ago |
 amritahs-ibm
|
13731766db
llamafile : ppc64le GEMV forwarding for FP32. (#12594)
|
10 months ago |
|
amritahs-ibm
|
c7b43ab608
llamafile : ppc64le MMA implementation for Q4_0. (#12489)
|
10 months ago |
 Jeffrey Morgan
|
8a8c4ceb60
llamafile: use member variable instead of constant for iq4nlt (#11780)
|
1 year ago |
|
amritahs-ibm
|
8cef75c743
llamafile : ppc64le MMA INT8 implementation (#10912)
|
1 year ago |
 Srihari-mcw
|
0827b2c1da
ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027)
|
1 year ago |
 Djip007
|
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
|
1 year ago |
|
Diego Devesa
|
9177484f58
ggml : fix arm build (#10890)
|
1 year ago |
|
Diego Devesa
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
1 year ago |
 Georgi Gerganov
|
db4cfd5dbc
llamafile : fix include path (#0)
|
1 year ago |
|
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
