| Age | Commit message (Expand) | Author |
|---|
| 2024-06-15 | [SYCL] remove global variables (#7710) | Meng, Hengyu |
| 2024-06-13 | move BLAS to a separate backend (#6210) | slaren |
| 2024-06-12 | tests : add non-cont unary tests (#7857) | Georgi Gerganov |
| 2024-06-10 | use the correct SYCL context for host USM allocations (#7777) | Ben Ashbaugh |
| 2024-06-07 | [SYCL] fix softmax r2r result wrong issue (#7811) | pengxin99 |
| 2024-06-05 | ggml : refactor rope norm/neox (#7634) | Georgi Gerganov |
| 2024-05-29 | ggml : fix YARN + add tests + add asserts (#7617) | Georgi Gerganov |
| 2024-05-29 | [SYCL] Align GEMM dispatch (#7566) | Meng, Hengyu |
| 2024-05-28 | sycl : fix assert (#7563) | Georgi Gerganov |
| 2024-05-28 | [SYCL]fix ggml_sycl_mul_mat_id() to match the change of api (#7436) | Neo Zhang |
| 2024-05-28 | ggml : generalize GGML_OP_CONCAT (#7563) | Georgi Gerganov |
| 2024-05-27 | Fix q_xxs using mul_mat_q (#7459) | AidanBeltonS |
| 2024-05-27 | Add freq factors (#7495) | AidanBeltonS |
| 2024-05-23 | ggml : drop support for QK_K=64 (#7473) | Georgi Gerganov |
| 2024-05-21 | llama : add phi3 128K model support (#7225) | liuwei-git |
| 2024-05-20 | [SYCL] Update SYCL upscale operation (#7321) | AidanBeltonS |
| 2024-05-15 | Add missing " (#7303) | AidanBeltonS |
| 2024-05-15 | ggml : add `ggml_upscale_ext` (ggml/814) | John Balis |
| 2024-05-13 | [SYCL] rm wait() (#7233) | Neo Zhang |
| 2024-05-11 | ggml : full ALiBi support (#7192) | Georgi Gerganov |
| 2024-05-10 | Minor arithmetic improvement to mmvq wrapper kernel (#7172) | Ouadie EL FAROUKI |
| 2024-04-30 | ggml : add Flash Attention (#5021) | Georgi Gerganov |
| 2024-04-28 | add device version in device list (#6959) | Neo Zhang |
| 2024-04-18 | ggml : group all experts in a single ggml_mul_mat_id (#6505) | slaren |
| 2024-04-15 | fix mul_mat_id() for new input, make the ut pass (#6682) | Neo Zhang Jianyu |
| 2024-04-14 | fix memcpy() crash, add missed cmd in guide, fix softmax (#6622) | Neo Zhang Jianyu |
| 2024-04-08 | remove row=1 cond (#6532) | Abhilash Majumder |
| 2024-04-07 | support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_T... | Neo Zhang Jianyu |
| 2024-04-05 | [SYCL] Fixed minor bug when enabling FP16 for non intel targets (#6464) | Ouadie EL FAROUKI |
| 2024-04-03 | [SYCL] Disable iqx on windows as WA (#6435) | Meng, Hengyu |
| 2024-03-28 | [SYCL] fix set main gpu crash (#6339) | Neo Zhang Jianyu |
| 2024-03-27 | [SYCL] Fix batched impl for NVidia GPU (#6164) | AidanBeltonS |
| 2024-03-26 | llama : greatly reduce output buffer memory usage (#6122) | compilade |
| 2024-03-24 | [SYCL] offload op (#6217) | Meng, Hengyu |
| 2024-03-21 | Add nvidia and amd backends (#6157) | AidanBeltonS |
| 2024-03-18 | backend : offload large batches to GPU (#6083) | slaren |
| 2024-03-15 | fix set main gpu error (#6073) | Neo Zhang Jianyu |
| 2024-03-15 | [SYCL] Fix non-intel device selection (#6042) | AidanBeltonS |
| 2024-03-13 | llama : add pipeline parallelism support (#6017) | slaren |
| 2024-03-13 | Update get version (#6025) | AidanBeltonS |
| 2024-03-12 | ggml : reuse quantum structs across backends (#5943) | Georgi Gerganov |
| 2024-03-12 | sycl : update IQ1_S kernels (WIP - not working!) (#5995) | Georgi Gerganov |
| 2024-03-11 | [SYCL] Add q3_s and q1_s (#5886) | Abhilash Majumder |
| 2024-03-09 | ggml : add ggml-common.h to deduplicate shared code (#5940) | Georgi Gerganov |
| 2024-03-07 | Revert "[SYCL] fix error when set main gpu to non-zero (#5901)" (#5918) | Neo Zhang Jianyu |
| 2024-03-07 | [SYCL] fix error when set main gpu to non-zero (#5901) | Neo Zhang Jianyu |
| 2024-03-06 | add wait() to make code stable (#5895) | Neo Zhang Jianyu |
| 2024-03-05 | [SYCL] fix mul_mat fault in CI/unit-test (#5862) | Neo Zhang Jianyu |
| 2024-03-04 | ggml : introduce ggml_status (ggml/750) | Michael Podvitskiy |
| 2024-03-02 | Support multiple GPUs (split mode) on SYCL backend (#5806) | Neo Zhang Jianyu |
