Default Branch

master a7a6d0d269 · vulkan: extend topk_moe fusion to support sqrt(softplus) (#26124) · Updated 2026-08-01 14:18:07 -05:00

ZIP  TAR.GZ

Branches

speculative-grammar c79d130f74 · make : fix speculative build · Updated 2023-09-04 07:50:04 -05:00    upstream-archive	9047 9		ZIP  TAR.GZ
speculative 847896aba7 · speculative : add --draft CLI arg · Updated 2023-09-03 05:51:07 -05:00    upstream-archive	9053 3		ZIP  TAR.GZ
norm-quants 8c2b881281 · cuda : poc for norm quants (only -b 1 works) · Updated 2023-08-30 13:42:28 -05:00    upstream-archive	9094 3		ZIP  TAR.GZ
norm-quants-rebase b4e70822f6 · metal : add poc for normalized Q4_0 and Q4_1 · Updated 2023-08-30 10:47:16 -05:00    upstream-archive	9094 7		ZIP  TAR.GZ
gguf-publish-ci 488e03200e · Merge branch 'master' into gguf-publish-ci · Updated 2023-08-30 03:34:55 -05:00    upstream-archive	9099 4		ZIP  TAR.GZ
gguf-64bit 33a5517d87 · llama.cpp : print gguf version · Updated 2023-08-26 16:56:48 -05:00    upstream-archive	9141 10		ZIP  TAR.GZ
ik/fix_hellaswag d34472c124 · Fix HellaSwag · Updated 2023-08-26 02:55:39 -05:00    upstream-archive	9154 1		ZIP  TAR.GZ
gguf-pip 0248ca811e · gguf : add notes for tests · Updated 2023-08-25 01:08:05 -05:00    upstream-archive	9166 10		ZIP  TAR.GZ
fix-eos 977629a34e · Merge branch 'master' into fix-eos · Updated 2023-08-23 14:40:19 -05:00    upstream-archive	9182 4		ZIP  TAR.GZ
gguf 66a66a05a8 · readme : add notice about new file format · Updated 2023-08-21 14:42:14 -05:00    upstream-archive	9211 253		ZIP  TAR.GZ
gguf-write-single-pass 6a9e6375b5 · gguf.py : indentation · Updated 2023-08-17 13:53:15 -05:00    upstream-archive	9226 205		ZIP  TAR.GZ
server-cfg 28046d1e52 · Merge and update · Updated 2023-08-08 16:36:11 -05:00    upstream-archive	9279 12		ZIP  TAR.GZ
gguf-write-tensor 511055722e · undo formatting · Updated 2023-07-28 01:09:14 -05:00    upstream-archive	9308 26		ZIP  TAR.GZ
gguf-python af1c9966c8 · gguf : start write tensor info · Updated 2023-07-27 02:32:31 -05:00    upstream-archive	9308 15		ZIP  TAR.GZ
ggml-backends d273bfd2c9 · allocator: cleanup, more comments · Updated 2023-07-22 08:05:24 -05:00    upstream-archive	9379 21		ZIP  TAR.GZ
ggml-backends-metal d45c1631bc · metal : rewrite to fit new backend interface correctly (WIP) · Updated 2023-07-20 14:51:19 -05:00    upstream-archive	9379 18		ZIP  TAR.GZ
refactor-mpi 0492363137 · mpi : fix after master merge · Updated 2023-07-09 14:23:04 -05:00    upstream-archive	9410 21		ZIP  TAR.GZ
llama_server_completions 26cc1bd7a2 · llama : uniform variable names + struct init · Updated 2023-07-05 15:22:17 -05:00    upstream-archive	9427 4		ZIP  TAR.GZ
llama_server_timings ff6e39f138 · use javascript generators as much cleaner API · Updated 2023-07-05 14:03:01 -05:00    upstream-archive	9440 20		ZIP  TAR.GZ
test-mac-os-ci f46db27ea0 · ci : disable FMA on Mac OS · Updated 2023-07-05 10:29:08 -05:00    upstream-archive	9437 5		ZIP  TAR.GZ