Default Branch

master 382808c14b · ci : re-enable rocm build on amd64 (#18439) · Updated 2025-12-28 15:29:23 -08:00

ZIP  TAR.GZ

Branches

Search

sycl-onednn-convolution 6494509801 · backup · Updated 2024-08-26 01:58:54 -07:00	3948 2		ZIP  TAR.GZ
gg/remove-k-quants-per-iter ccb45186d0 · docs : remove references · Updated 2024-08-25 23:52:17 -07:00	3942 2		ZIP  TAR.GZ
compilade/batch-splits 8062650343 · llama : fix simple splits when the batch contains embeddings · Updated 2024-08-21 12:09:03 -07:00	3953 19		ZIP  TAR.GZ
sl/prepare-next-graph 9127800d83 · wip · Updated 2024-08-16 16:51:06 -07:00	3986 2		ZIP  TAR.GZ
gg/hf-test 62d7b6c87f · cuda : re-add q4_0 · Updated 2024-08-14 03:37:03 -07:00	3982 3		ZIP  TAR.GZ
compilade/fix-server-long-system-prompt 93ec58b932 · server : fix typo in comment · Updated 2024-08-13 19:12:26 -07:00	3984 4		ZIP  TAR.GZ
compilade/nul-str-token faaac59d16 · llama : support NUL bytes in tokens · Updated 2024-08-11 18:00:03 -07:00	3995 1		ZIP  TAR.GZ
compilade/gguf-py-dequant 73bc9350cd · gguf-py : Numpy dequantization for grid-based i-quants · Updated 2024-08-09 20:47:31 -07:00	4015 2		ZIP  TAR.GZ
compilade/faster-session-sizes 9329953a61 · llama : avoid double tensor copy when saving session to buffer · Updated 2024-08-07 13:03:34 -07:00	4023 2		ZIP  TAR.GZ
update_sycl_doc 7764ab911d · update guide · Updated 2024-08-07 07:01:02 -07:00	4024 1		ZIP  TAR.GZ
sl/dump-allocs cad8abb49b · add tool to allow plotting tensor allocation maps within buffers · Updated 2024-08-06 13:09:51 -07:00	4032 1		ZIP  TAR.GZ
prepare-PR-of-minicpm-v2.5-gg 6e299132e7 · clip : style changes · Updated 2024-08-06 01:44:29 -07:00	4356 56		ZIP  TAR.GZ
fix_cmd_name 16dab13bde · correct cmd name · Updated 2024-08-05 09:15:33 -07:00	4041 1		ZIP  TAR.GZ
gg/replace-all bddcc5f985 · llama : better replace_all · Updated 2024-08-04 03:42:08 -07:00	4057 1		ZIP  TAR.GZ
compilade/gguf-py-quants-class 229c35cb59 · gguf-py : remove LlamaFileTypeMap · Updated 2024-08-03 18:22:37 -07:00	4060 5		ZIP  TAR.GZ
codeplay/sycl-main eab4a88210 · Using dp4a ptx intrinsics for an improved Mul8MAT perf [By Alcpz] · Updated 2024-07-29 08:52:29 -07:00	4078 1		ZIP  TAR.GZ
compilade/refactor-session-files 9cddd9aeec · llama : cast seq_id in comparison with unsigned n_seq_max · Updated 2024-07-27 12:50:23 -07:00	4116 7		ZIP  TAR.GZ
sycl-conv-op 9aeb0e1f75 · sycl add conv support · Updated 2024-07-25 05:15:02 -07:00	4105 1		ZIP  TAR.GZ
gg/system-info-llamafile 5934580905 · ggml : add and use ggml_cpu_has_llamafile() · Updated 2024-07-24 01:31:41 -07:00	4116 1		ZIP  TAR.GZ
gg/llama-reorganize fe28a7b9d8 · llama : clean-up · Updated 2024-07-22 22:38:50 -07:00	4124 11		ZIP  TAR.GZ