summaryrefslogtreecommitdiff
path: root/ggml-quants.h
AgeCommit message (Expand)Author
2024-04-09llama : add Command R Plus support (#6491)Carolinabanana
2024-03-26IQ1_M: 1.75 bpw quantization (#6302)Kawrakow
2024-03-12ggml : reuse quantum structs across backends (#5943)Georgi Gerganov
2024-03-11Better 1.5 bit quantization (#5971)Kawrakow
2024-03-09ggml : remove old quantization functions (#5942)Georgi Gerganov
2024-03-09ggml : add ggml-common.h to deduplicate shared code (#5940)Georgi Gerganov
2024-02-28ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (#5760)Kawrakow
2024-02-27IQ4_XS: a 4.25 bpw quantization (#5747)Kawrakow
2024-02-26Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range...Kawrakow
2024-02-24IQ3_S: a much better alternative to Q3_K (#5676)Kawrakow
2024-02-21IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)Kawrakow
2024-02-181.5 bit quantization (#5453)Kawrakow
2024-02-11ggml : add mmla kernels for quantized GEMM (#4966)snadampal
2024-02-05ggml : make use of ggml-quants.h possible in C++ code (#5338)Kawrakow
2024-01-30SOTA 3-bit quants (#5196)Kawrakow
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
2024-01-11ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)Kawrakow
2024-01-08SOTA 2-bit quants (#4773)Kawrakow
2024-01-05ggml : fix q2_k bpw in comments (ggml/680)Georgi Gerganov
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 22:51:22 +0000