Default Branch

master 11924d4c17 · test: fix some CI errors (#26415) · Updated 2026-08-01 17:16:29 -05:00

ZIP  TAR.GZ

Branches

gg/lfs 0fc560fe96 · ci : enable git lfs for build.yml · Updated 2024-05-08 02:53:02 -05:00    upstream-archive	7415 7		ZIP  TAR.GZ
compilade/convert-hf-refactor c32d39cefb · Merge branch 'master' into compilade/convert-hf-refactor · Updated 2024-05-06 04:33:38 -05:00    upstream-archive	7428 19		ZIP  TAR.GZ
gg/flash-attn c240ae234c · ci : fix arg order · Updated 2024-04-30 03:43:36 -05:00    upstream-archive	7458 145		ZIP  TAR.GZ
gg/tmp-ci 5ddad95e5c · ci : tmp disable gguf-split · Updated 2024-04-29 10:29:38 -05:00    upstream-archive	7459 1		ZIP  TAR.GZ
gg/bpe-preprocess 80cb3127df · tests : disable test-tokenizer-1-bpe due to slowness · Updated 2024-04-29 07:24:39 -05:00    upstream-archive	7471 61		ZIP  TAR.GZ
gg/fix-min-max 8c259f6f3e · ggml : fix MIN / MAX macros · Updated 2024-04-25 06:28:41 -05:00    upstream-archive	7496 1		ZIP  TAR.GZ
gg/add-phi-3-support 5dcccb3a7d · convert : fix tokenizer conversion · Updated 2024-04-23 14:11:09 -05:00    upstream-archive	7507 2		ZIP  TAR.GZ
test-bench 124e4dced2 · Update · Updated 2024-04-22 04:42:32 -05:00    upstream-archive	7564 2		ZIP  TAR.GZ
gg/llama3-support 3750706962 · llama : add llama_token_is_eog() · Updated 2024-04-20 08:52:03 -05:00    upstream-archive	7529 4		ZIP  TAR.GZ
gg/disable-sgemm f02ea667c1 · ggml : temporary disable llamafile sgemm until fixed · Updated 2024-04-16 14:45:56 -05:00    upstream-archive	7538 1		ZIP  TAR.GZ
hp/tmp/kv-cache-defrag eedd42e376 · KV Cache defrag hash overflow - TMP Fix by @slaren · Updated 2024-04-16 03:24:34 -05:00    upstream-archive	7541 1		ZIP  TAR.GZ
gg/imatrix-remove-assert 8b495540fa · imatrix : remove invalid assert · Updated 2024-04-12 03:45:12 -05:00    upstream-archive	7566 1		ZIP  TAR.GZ
gg/authors 072e0a4d3b · scipts : add LICENSE and gen-authors.sh to sync · Updated 2024-04-09 01:19:33 -05:00    upstream-archive	7642 3		ZIP  TAR.GZ
ceb/bert-tokenizer-fixes a37696d4f1 · speculative : more robust tokenizer comparison · Updated 2024-04-04 17:28:13 -05:00    upstream-archive	7612 9		ZIP  TAR.GZ
gg/flash-attn-a 4c190ba676 · cuda : reduce registers · Updated 2024-03-28 14:17:08 -05:00    upstream-archive	7654 77		ZIP  TAR.GZ
compilade/fix-command-r 64b7d85891 · llama : fix command-r inference · Updated 2024-03-28 05:22:24 -05:00    upstream-archive	7659 1		ZIP  TAR.GZ
gg/flash-attn-wip 6be02b5969 · cuda : fix build · Updated 2024-03-27 03:31:52 -05:00    upstream-archive	7676 72		ZIP  TAR.GZ
ceb/wpm-portable-tolower 87a6088ffe · rename unicodedata.{cpp,h} to unicode-data.{cpp,h} · Updated 2024-03-26 09:52:33 -05:00    upstream-archive	7691 7		ZIP  TAR.GZ
ik/quantize_with_kv_overrides 9c5fd6be14 · minor : spacing · Updated 2024-03-26 07:09:02 -05:00    upstream-archive	7689 2		ZIP  TAR.GZ
ik/test_quantize_fns 6f20e2672f · Include IQ2_XXS and IQ2_XS in teet-quantize-fns · Updated 2024-03-25 12:01:20 -05:00    upstream-archive	7693 1		ZIP  TAR.GZ