Default branch

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

ZIP  TAR.GZ

Branches

gg/add-phi-3-support 5dcccb3a7d · convert : fix tokenizer conversion · Updated 2024-04-23 19:11:09 +00:00    vbatts	1965 2	Compare	ZIP  TAR.GZ
test-bench 124e4dced2 · Update · Updated 2024-04-22 09:42:32 +00:00    vbatts	2022 2	Compare	ZIP  TAR.GZ
gg/llama3-support 3750706962 · llama : add llama_token_is_eog() · Updated 2024-04-20 13:52:03 +00:00    vbatts	1987 4	Compare	ZIP  TAR.GZ
gg/disable-sgemm f02ea667c1 · ggml : temporary disable llamafile sgemm until fixed · Updated 2024-04-16 19:45:56 +00:00    vbatts	1996 1	Compare	ZIP  TAR.GZ
hp/tmp/kv-cache-defrag eedd42e376 · KV Cache defrag hash overflow - TMP Fix by @slaren · Updated 2024-04-16 08:24:34 +00:00    vbatts	1999 1	Compare	ZIP  TAR.GZ
gg/imatrix-remove-assert 8b495540fa · imatrix : remove invalid assert · Updated 2024-04-12 08:45:12 +00:00    vbatts	2024 1	Compare	ZIP  TAR.GZ
gg/authors 072e0a4d3b · scipts : add LICENSE and gen-authors.sh to sync · Updated 2024-04-09 06:19:33 +00:00    vbatts	2100 3	Compare	ZIP  TAR.GZ
ceb/bert-tokenizer-fixes a37696d4f1 · speculative : more robust tokenizer comparison · Updated 2024-04-04 22:28:13 +00:00    vbatts	2070 9	Compare	ZIP  TAR.GZ
gg/flash-attn-a 4c190ba676 · cuda : reduce registers · Updated 2024-03-28 19:17:08 +00:00    vbatts	2112 77	Compare	ZIP  TAR.GZ
compilade/fix-command-r 64b7d85891 · llama : fix command-r inference · Updated 2024-03-28 10:22:24 +00:00    vbatts	2117 1	Compare	ZIP  TAR.GZ
gg/flash-attn-wip 6be02b5969 · cuda : fix build · Updated 2024-03-27 08:31:52 +00:00    vbatts	2134 72	Compare	ZIP  TAR.GZ
ceb/wpm-portable-tolower 87a6088ffe · rename unicodedata.{cpp,h} to unicode-data.{cpp,h} · Updated 2024-03-26 14:52:33 +00:00    vbatts	2149 7	Compare	ZIP  TAR.GZ
ik/quantize_with_kv_overrides 9c5fd6be14 · minor : spacing · Updated 2024-03-26 12:09:02 +00:00    vbatts	2147 2	Compare	ZIP  TAR.GZ
ik/test_quantize_fns 6f20e2672f · Include IQ2_XXS and IQ2_XS in teet-quantize-fns · Updated 2024-03-25 17:01:20 +00:00    vbatts	2151 1	Compare	ZIP  TAR.GZ
sl/cuda-f16-fix3 210e469114 · cuda : fix LLAMA_CUDA_F16 build · Updated 2024-03-25 14:31:10 +00:00    vbatts	2153 1	Compare	ZIP  TAR.GZ
ceb/fix-win-unicode-fpaths d05c13b3b9 · llama : fix BPE LF token on MSVC · Updated 2024-03-23 18:03:16 +00:00    vbatts	2173 3	Compare	ZIP  TAR.GZ
gg/flash-attn-rebase 3a468e6f9f · llama : fix type of KQ_mask and KQ_pos · Updated 2024-03-22 15:12:17 +00:00    vbatts	2178 68	Compare	ZIP  TAR.GZ
ik/quantize_not_repeating 0e826d12a5 · quantize: be able to specify the token embedding tensor type · Updated 2024-03-22 14:27:34 +00:00    vbatts	2187 2	Compare	ZIP  TAR.GZ
gg/hf-args 8c3d5b5a79 · common : remove defaults · Updated 2024-03-22 13:33:24 +00:00    vbatts	2183 2	Compare	ZIP  TAR.GZ
patch-1 12aa74ba7d · minor : spacing · Updated 2024-03-22 13:24:57 +00:00    vbatts	2408 6	Compare	ZIP  TAR.GZ