llama.cpp

master

d7b31a9d84 · sync: minja (a72057e519) (#11774) · Updated 2025-02-10 09:34:09 +00:00

sycl-onednn-convolution 6494509801 · backup · Updated 2024-08-26 08:58:54 +00:00 vbatts	1064 2		ZIP TAR.GZ
gg/remove-k-quants-per-iter ccb45186d0 · docs : remove references · Updated 2024-08-26 06:52:17 +00:00 vbatts	1058 2		ZIP TAR.GZ
compilade/batch-splits 8062650343 · llama : fix simple splits when the batch contains embeddings · Updated 2024-08-21 19:09:03 +00:00 vbatts	1069 19		ZIP TAR.GZ
sl/prepare-next-graph 9127800d83 · wip · Updated 2024-08-16 23:51:06 +00:00 vbatts	1102 2		ZIP TAR.GZ
gg/hf-test 62d7b6c87f · cuda : re-add q4_0 · Updated 2024-08-14 10:37:03 +00:00 vbatts	1098 3		ZIP TAR.GZ
compilade/fix-server-long-system-prompt 93ec58b932 · server : fix typo in comment · Updated 2024-08-14 02:12:26 +00:00 vbatts	1100 4		ZIP TAR.GZ
compilade/nul-str-token faaac59d16 · llama : support NUL bytes in tokens · Updated 2024-08-12 01:00:03 +00:00 vbatts	1111 1		ZIP TAR.GZ
compilade/gguf-py-dequant 73bc9350cd · gguf-py : Numpy dequantization for grid-based i-quants · Updated 2024-08-10 03:47:31 +00:00 vbatts	1131 2		ZIP TAR.GZ
compilade/faster-session-sizes 9329953a61 · llama : avoid double tensor copy when saving session to buffer · Updated 2024-08-07 20:03:34 +00:00 vbatts	1139 2		ZIP TAR.GZ
update_sycl_doc 7764ab911d · update guide · Updated 2024-08-07 14:01:02 +00:00 vbatts	1140 1		ZIP TAR.GZ
sl/dump-allocs cad8abb49b · add tool to allow plotting tensor allocation maps within buffers · Updated 2024-08-06 20:09:51 +00:00 vbatts	1148 1		ZIP TAR.GZ
prepare-PR-of-minicpm-v2.5-gg 6e299132e7 · clip : style changes · Updated 2024-08-06 08:44:29 +00:00 vbatts	1472 56		ZIP TAR.GZ
fix_cmd_name 16dab13bde · correct cmd name · Updated 2024-08-05 16:15:33 +00:00 vbatts	1157 1		ZIP TAR.GZ
gg/replace-all bddcc5f985 · llama : better replace_all · Updated 2024-08-04 10:42:08 +00:00 vbatts	1173 1		ZIP TAR.GZ
compilade/gguf-py-quants-class 229c35cb59 · gguf-py : remove LlamaFileTypeMap · Updated 2024-08-04 01:22:37 +00:00 vbatts	1176 5		ZIP TAR.GZ
codeplay/sycl-main eab4a88210 · Using dp4a ptx intrinsics for an improved Mul8MAT perf [By Alcpz] · Updated 2024-07-29 15:52:29 +00:00 vbatts	1194 1		ZIP TAR.GZ
compilade/refactor-session-files 9cddd9aeec · llama : cast seq_id in comparison with unsigned n_seq_max · Updated 2024-07-27 19:50:23 +00:00 vbatts	1232 7		ZIP TAR.GZ
sycl-conv-op 9aeb0e1f75 · sycl add conv support · Updated 2024-07-25 12:15:02 +00:00 vbatts	1221 1		ZIP TAR.GZ
vbatts-finetune Some checks failed flake8 Lint / Lint (push) Has been cancelled Details 4b0eff3df5 · docs : Quantum -> Quantized (#8666) · Updated 2024-07-25 08:13:27 +00:00 vbatts	1224 0	Included	ZIP TAR.GZ
gg/system-info-llamafile 5934580905 · ggml : add and use ggml_cpu_has_llamafile() · Updated 2024-07-24 08:31:41 +00:00 vbatts	1232 1		ZIP TAR.GZ

... 3 4 5 6 7 ...

Default branch

Branches