summaryrefslogtreecommitdiff
path: root/ggml.c
AgeCommit message (Expand)Author
2024-07-18iqk_mul_mat: attentions matrix multiplicationsIwan Kawrakow
2024-07-17iq1bn: adjust scalar dot product and some cleanupIwan Kawrakow
2024-06-22bitnet: replace ggml_mul with ggml_scale to apply the scalesIwan Kawrakow
2024-06-22bitnet(scale in a separate tensor): mul -> scale on the CPUIwan Kawrakow
2024-06-22bitnet: add 2 bpw quantizationIwan Kawrakow
2024-06-22bitnet: CUDA, scalar, AVX2Iwan Kawrakow
2024-06-22iqk_mul_mat: be independent of llamafile_sgemm (WIP)Iwan Kawrakow
2024-06-22iqk_mul_mat: add ability to disable itIwan Kawrakow
2024-06-22iqk_mul_mat: make it build with the MakefileIwan Kawrakow
2024-06-22iqk_mul_mat: multi-thread quantization also for MoE modelsIwan Kawrakow
2024-06-22iqk_mul_mat: make it independent of sgemmIwan Kawrakow
2024-06-22iqk_mul_mat for llama.cppIwan Kawrakow
2024-06-19ggml : synchronize threads using barriers (#7993)slaren
2024-06-13move BLAS to a separate backend (#6210)slaren
2024-06-12tests : add non-cont unary tests (#7857)Georgi Gerganov
2024-06-12ggml : improve ggml_is_contiguous logic (#7856)Georgi Gerganov
2024-06-05ggml : refactor rope norm/neox (#7634)Georgi Gerganov
2024-06-04ggml : remove OpenCL (#7735)Georgi Gerganov
2024-06-04ggml : prevent builds with -ffinite-math-only (#7726)Georgi Gerganov
2024-06-03ggml : use OpenMP as a thread pool (#7606)Masaya, Kato
2024-05-31ggml : fix loongson compile warnings (#7537)Georgi Gerganov
2024-05-30faster avx512 exp implementation (#7551)Chris Elrod
2024-05-30ggml : fix loongarch build (O2 issue) (#7636)junchao-loongson
2024-05-29ggml : fix YARN + add tests + add asserts (#7617)Georgi Gerganov
2024-05-29llama-bench : add support for the RPC backend (#7435)Radoslav Gerganov
2024-05-29ggml : use atomic_flag for critical section (#7598)slaren
2024-05-29ggml : restore ggml_rope_xpos_inplace (ggml/0)Georgi Gerganov
2024-05-29ggml : fix typo in ggml.c (#7603)zhouwg
2024-05-28ggml : generalize GGML_OP_CONCAT (#7563)Georgi Gerganov
2024-05-25ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)Masaya, Kato
2024-05-23ggml : remove ggml_flash_attn and ggml_flash_ff (#7463)Georgi Gerganov
2024-05-23ggml : drop support for QK_K=64 (#7473)Georgi Gerganov
2024-05-22cuda : fix rope + add tests (#7452)Georgi Gerganov
2024-05-21llama : add phi3 128K model support (#7225)liuwei-git
2024-05-20ggml : add loongarch lsx and lasx support (#6454)junchao-loongson
2024-05-20Add provisions for windows support for BF16 code including CMake provision fo...Srihari-mcw
2024-05-19ggml: implement quantized KV cache for FA (#7372)Johannes Gäßler
2024-05-18android : use "ci-android" branch for CI (#7341)Georgi Gerganov
2024-05-17ggml : rewrite silu and softmax for cpu (#7154)Justine Tunney
2024-05-15ggml : use dynamic thread scheduling for matrix multiplication (#6915)kunnis
2024-05-15ggml : tag ggml_tensor::backend as deprecated (#7290)slaren
2024-05-15ggml : add `ggml_upscale_ext` (ggml/814)John Balis
2024-05-14metal : support FA without mask + add asserts (#7278)Georgi Gerganov
2024-05-14ggml : try fix ppc64 (whisper/0)Georgi Gerganov
2024-05-11ggml : resolve merge (ggml/0)Georgi Gerganov
2024-05-11feat: implemented sigmoid function (ggml/806)Justina Cho
2024-05-11ggml : full ALiBi support (#7192)Georgi Gerganov
2024-05-08ggml : introduce bfloat16 support (#6412)Justine Tunney
2024-05-04gguf-split: add --no-tensor-first-split (#7072)Xuan Son Nguyen
2024-04-30ggml : add Flash Attention (#5021)Georgi Gerganov
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-08 12:43:35 +0000