Default Branch

master 30caac3a68 · llama : the WPM vocabs use the CLS token as BOS (#10930) · Updated 2024-12-24 08:44:20 +01:00

ZIP  TAR.GZ

Branches

compilade/pyright-fix-ignores a34fc0dd86 · ci : reduce severity of unused Pyright ignore comments · Updated 2024-09-30 19:59:40 +02:00	537 1		ZIP  TAR.GZ
gg/tfs-ob1 114ab6347e · sampling : fix off-by-one in tail-free sampling · Updated 2024-09-23 10:44:55 +02:00	581 1		ZIP  TAR.GZ
gg/tokenizer-cleanup 6e873e561a · llama : make llm_tokenizer more private · Updated 2024-09-20 10:41:51 +02:00	600 2		ZIP  TAR.GZ
sl/fix-omp-one-thread 6b0248c29a · Update ggml/src/ggml.c · Updated 2024-09-18 18:00:26 +02:00	605 2		ZIP  TAR.GZ
fix_ctx_default a6a8f8d09c · Update docs/backend/SYCL.md · Updated 2024-09-17 10:25:43 +02:00	637 2		ZIP  TAR.GZ
gg/cb-naming cc1c017191 · naming : normalize the name of callback-related identifiers · Updated 2024-09-16 08:11:42 +02:00	625 1		ZIP  TAR.GZ
sycl-cmake-append 73ef3f769c · Update llama-server-intel.Dockerfile · Updated 2024-09-15 17:21:46 +02:00	630 3		ZIP  TAR.GZ
gg/cmake-dedup-link fb8f142554 · one more CMAKE_CXX_FLAGS fix (#9471) · Updated 2024-09-13 15:13:07 +02:00	639 5		ZIP  TAR.GZ
gg/ggml-atomic-int d7c042d1ae · ggml : make n_threads_cur atomic_int · Updated 2024-09-11 20:12:11 +02:00	655 1		ZIP  TAR.GZ
gg/ggml-rework-cgraph f9968f661d · ggml : update comments [no ci] · Updated 2024-09-11 12:16:39 +02:00	668 5		ZIP  TAR.GZ
compilade/imatrix-batched-chunks 2d79a7077c · quantize : use unused imatrix chunk_size with LLAMA_TRACE · Updated 2024-09-10 18:09:17 +02:00	685 13		ZIP  TAR.GZ
SVE-vector-length-agnostic-VLA-gg cfbf33a705 · ggml : style changes + fix 512-bit nb loop check · Updated 2024-09-09 11:50:35 +02:00	729 4		ZIP  TAR.GZ
sl/fix-rpc-nkvo c3e2bb6dcf · rpc : fix nkvo · Updated 2024-09-07 03:24:47 +02:00	710 1		ZIP  TAR.GZ
fix-ninja-metallib-build b979fc97ba · cmake : use ggml-metal.metal from source dir to build default.metallib · Updated 2024-09-05 18:17:56 +02:00	719 1		ZIP  TAR.GZ
compilade/bitnet-ternary 75b3a09602 · test-backend-ops : add TQ1_0 and TQ2_0 comments for later · Updated 2024-09-04 21:00:21 +02:00	721 33		ZIP  TAR.GZ
gg/llama-refactor-sampling f648ca2cee · llama : add llama_sampling API + move grammar in libllama · Updated 2024-09-03 09:31:54 +02:00	728 1		ZIP  TAR.GZ
gg/llama-disambiguate 40fa68cb46 · readme : add API change notice · Updated 2024-09-02 17:32:24 +02:00	737 3		ZIP  TAR.GZ
compilade/refactor-kv-cache 375de5b1f8 · llama : use unused n_embd_k_gqa in k_shift · Updated 2024-09-02 03:59:24 +02:00	737 41		ZIP  TAR.GZ
gg/metal-fix-fa-2 a95225cdfd · metal : another fix for the fa kernel · Updated 2024-08-26 14:08:38 +02:00	761 1		ZIP  TAR.GZ
gg/metal-fix-fa aa931d0375 · metal : fix fa kernel · Updated 2024-08-26 12:09:50 +02:00	761 1		ZIP  TAR.GZ