COMMITS
/ tests/test-quantize-fns.cpp March 11, 2026
R
ggml : add NVFP4 quantization type support (#19769)
Richard Davison committed
March 10, 2025
G
tests : fix test-quantize-fns to init the CPU backend (#12306)
Georgi Gerganov committed
November 25, 2024
G
tests : fix compile warning
Georgi Gerganov committed
November 14, 2024
D
ggml : build backends as libraries (#10256)
Diego Devesa committed
November 3, 2024
D
ggml : move CPU backend to a separate file (#10144)
Diego Devesa committed
October 8, 2024
D
ggml : fix BLAS with unsupported types (#9775)
Diego Devesa committed
September 6, 2024
C
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
compilade committed
July 12, 2024
G
ggml : minor naming changes (#8433)
Georgi Gerganov committed
March 25, 2024
K
tests : include IQ2_XXS and IQ2_XS in test-quantize-fns (#6303)
Kawrakow committed
February 26, 2024
February 24, 2024
K
IQ3_S: a much better alternative to Q3_K (#5676)
Kawrakow committed
February 11, 2024
S
ggml : add mmla kernels for quantized GEMM (#4966)
snadampal committed
January 30, 2024
K
SOTA 3-bit quants (#5196)
Kawrakow committed
January 11, 2024
K
ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)
Kawrakow committed
January 8, 2024
K
SOTA 2-bit quants (#4773)
Kawrakow committed
October 30, 2023
G
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)
Georgi Gerganov committed
September 15, 2023
C
check C++ code with -Wmissing-declarations (#3184)
Cebtenzzre committed
July 5, 2023
S
ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)
Stephan Walter committed
June 16, 2023
B
build : fix and ignore MSVC warnings (#1889)
Borislav Stanimirov committed
June 5, 2023
K
ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684)
Kawrakow committed
April 25, 2023
G
ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)
Georgi Gerganov committed
April 22, 2023
S
Fix CI: ARM NEON, quantization unit tests, editorconfig (#1122)
Stephan Walter committed
U
ggml : unit test for quantization functions (#953)
unbounded committed