index
:
ik_llama.cpp.git
main
Unnamed repository; edit this file 'description' to name the repository.
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
k_quants.c
Age
Commit message (
Expand
)
Author
2023-09-12
arm64 support for windows (#3007)
Eric Sommerlade
2023-09-06
k-quants : fix zero-weight guard in Q6_K (ref #3040)
Georgi Gerganov
2023-09-05
Guard against all weights in a super-block being zero (#3010)
Kawrakow
2023-09-02
k-quants : fix build on armv7 (android only) (#2920)
Jhen-Jie Hong
2023-09-01
build : fix most gcc and clang warnings (#2861)
Cebtenzzre
2023-08-28
ggml : tiny ggml_vec_dot_q4_K_q8_K AVX2 improvement (#2819)
Ronny Brendel
2023-08-22
Quantization imrovements for k_quants (#2707)
Kawrakow
2023-07-28
ggml : workaround for missing _mm256_setr_m128i in GCC < 8 in k_quants.c (#2405)
Lee
2023-07-25
k_quants : add AVX support to dot functions with QK_K as 64 (#2339)
katsu560
2023-07-24
Fix scalar version of Q5_K when QK_K = 64 (#2362)
Kawrakow
2023-06-26
k-quants : fix indentation
Georgi Gerganov
2023-06-26
k-quants : add AVX support to dot functions (#1916)
katsu560
2023-06-26
k-quants : support for super-block size of 64 (#2001)
Kawrakow
2023-06-10
k-quants : GCC12 compilation fix (#1792)
Artyom Lebedev
2023-06-08
Revert "ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)"
Georgi Gerganov
2023-06-08
ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)
le.chang
2023-06-07
k-quants : allow to optionally disable at compile time (#1734)
Georgi Gerganov