summaryrefslogtreecommitdiff
path: root/ggml-quants.c
AgeCommit message (Expand)Author
2024-01-17ggml : add IQ2 to test-backend-ops + refactoring (#4990)Georgi Gerganov
2024-01-16ggml : importance matrix support for legacy quants (#4969)Kawrakow
2024-01-14Add ability to use importance matrix for all k-quants (#4930)Kawrakow
2024-01-142-bit quantizations (#4897)Kawrakow
2024-01-12ggml : fix 32-bit ARM compat for IQ2_XS (whisper/1758)Georgi Gerganov
2024-01-11ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)Kawrakow
2024-01-09ggml : fix vld1q_s8_x4 32-bit compat (#4828)Georgi Gerganov
2024-01-08SOTA 2-bit quants (#4773)Kawrakow
2023-12-31ggml : add ggml_vdotq_s32 alias (#4715)Georgi Gerganov
2023-12-27ggml : fix dot product for ARM (#4630)Georgi Gerganov
2023-12-22cuda : fix jetson compile error (#4560)FantasyGmm
2023-12-12english : use `typos` to fix comments and logs (#4354)Richard Kiss
2023-11-17build : support ppc64le build for make and CMake (#3963)Roger Meier
2023-11-14Fix MacOS Sonoma model quantization (#4052)Michael Potter
2023-11-13ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060)Georgi Gerganov
2023-11-01ggml : fix UNUSED macro (#3762)Georgi Gerganov
2023-11-01finetune : add -ngl parameter (#3762)Andrew Godfrey
2023-10-30ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)Georgi Gerganov
2023-10-29ggml : quantization refactoring (#3833)Georgi Gerganov
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-04 16:54:41 +0000