Default Branch

master 76a5bc86d1 · common : use fs::path for cache dirs (#29595) · Updated 2026-09-29 00:24:03 -05:00

ZIP  TAR.GZ

Branches

ci/server/fix-slow-test eb0bf32caf · server: tests: schedule slow dispatch only on release or on demand · Updated 2024-03-02 16:18:31 -06:00    upstream-archive	8924 1		ZIP  TAR.GZ
ceb/convert-hf-refactor 0b673ca187 · s/_MODEL_CLASSES/_model_classes/ · Updated 2024-03-02 11:14:37 -06:00    upstream-archive	8937 3		ZIP  TAR.GZ
ik/iq3_s_faster d4dfc250cc · Fix ARM_NEON · Updated 2024-03-02 02:12:02 -06:00    upstream-archive	8942 7		ZIP  TAR.GZ
ceb/convert-vocab-fallback f8ab539190 · convert : update help string · Updated 2024-03-01 11:29:34 -06:00    upstream-archive	8940 3		ZIP  TAR.GZ
gg/fix-starcoder2 9862d59c05 · llama : change starcoder2 rope type · Updated 2024-03-01 07:10:31 -06:00    upstream-archive	8949 8		ZIP  TAR.GZ
ik/i-quants-64 f0cbb6ddf6 · iq1_s: turn off SIMD implementation for QK_K = 64 (it does not work) · Updated 2024-02-28 00:28:10 -06:00    upstream-archive	8964 6		ZIP  TAR.GZ
gg/kv-compress 14d757066b · llama : add llama_kv_cache_compress (EXPERIMENTAL) · Updated 2024-02-27 08:24:40 -06:00    upstream-archive	8965 1		ZIP  TAR.GZ
gg/float-pos 608f449880 · swift : fix build · Updated 2024-02-23 11:02:09 -06:00    upstream-archive	8996 4		ZIP  TAR.GZ
gg/py-minor-fixes 56c047156a · py : minor fixes · Updated 2024-02-22 11:22:56 -06:00    upstream-archive	9005 1		ZIP  TAR.GZ
sl/fix-quant-kv-shift 5271c75666 · llama : fix K-shift with quantized K (wip) · Updated 2024-02-21 17:28:42 -06:00    upstream-archive	9013 1		ZIP  TAR.GZ
gg/flash-attn-sync f249c997a8 · llama : adapt to F16 KQ_pos · Updated 2024-02-19 05:31:02 -06:00    upstream-archive	9051 62		ZIP  TAR.GZ
gg/metal-batched 412735ec70 · Merge branch 'master' into gg/metal-batched · Updated 2024-02-19 03:25:24 -06:00    upstream-archive	9051 6		ZIP  TAR.GZ
gg/rename-n_ctx 47c662b0de · fix some spaces added by IDE in math op · Updated 2024-02-18 14:40:35 -06:00    upstream-archive	9061 4		ZIP  TAR.GZ
gg/fix-android 974e3cadff · ggml : try another fix · Updated 2024-02-17 10:14:35 -06:00    upstream-archive	9080 2		ZIP  TAR.GZ
gg/hf e856bfed3b · hf : add support for --repo and --file · Updated 2024-02-15 07:05:15 -06:00    upstream-archive	9094 3		ZIP  TAR.GZ
ceb/nomic-bert ccd757a174 · convert : fix mistakes from refactoring · Updated 2024-02-13 11:01:30 -06:00    upstream-archive	9102 4		ZIP  TAR.GZ
ik/iq1_s 5c977221d2 · iq1_s: slightly faster dot product · Updated 2024-02-13 07:18:27 -06:00    upstream-archive	9108 15		ZIP  TAR.GZ
ik/fix_warnings 4246b71ad7 · Fix compiler warnings (shadow variable) · Updated 2024-02-13 00:44:56 -06:00    upstream-archive	9111 1		ZIP  TAR.GZ
ceb/bert 7286b83d3f · BERT WIP · Updated 2024-02-06 16:10:11 -06:00    upstream-archive	9164 1		ZIP  TAR.GZ
gg/convert-fix-byte-tokens adcf16fd68 · py : fix empty bytes arg · Updated 2024-02-05 11:53:07 -06:00    upstream-archive	9174 2		ZIP  TAR.GZ