Default Branch

master 592feef04a · talk-llama : sync llama.cpp · Updated 2026-08-07 22:59:49 +04:00

ZIP  TAR.GZ

Branches

metal-and-alloc 3ac0558009 · ios : update SPM package · Updated 2023-09-15 13:13:33 +04:00    LLM-Inference	4176 44		ZIP  TAR.GZ
fix-bench 09a6325de5 · ggml : use sched_yield when using BLAS + add comment · Updated 2023-09-12 14:33:09 +04:00    LLM-Inference	4177 2		ZIP  TAR.GZ
grammar-debug 3c50be2217 · whisper : remove comment · Updated 2023-09-10 14:27:06 +04:00    LLM-Inference	4194 9		ZIP  TAR.GZ
feature/debug-gradle-signing 9c1a414feb · use secrets.GPG_PRIVATE_KEY and GPG_PASSPHRASE · Updated 2023-09-09 18:49:13 +04:00    LLM-Inference	4179 5		ZIP  TAR.GZ
java-bindings 3efe146d27 · ci : enable java package publishing · Updated 2023-08-30 23:13:38 +04:00    LLM-Inference	4201 1		ZIP  TAR.GZ
fix-coreml-ane 8cbc363561 · coreml : attempt to fix ANE-optimized models · Updated 2023-07-12 00:03:53 +04:00    LLM-Inference	4239 1		ZIP  TAR.GZ
fix-vzip c6174cb868 · wip · Updated 2023-05-02 22:47:12 +04:00    LLM-Inference	4307 1		ZIP  TAR.GZ
llama-podcast c456ca476b · llama podcast · Updated 2023-04-01 14:13:27 +04:00    LLM-Inference	4375 1		ZIP  TAR.GZ
talk.llama-coreml 3627ef51f6 · minor · Updated 2023-03-27 00:54:52 +04:00    LLM-Inference	4392 7		ZIP  TAR.GZ
coreml-with-state 0244810697 · rebase on master after whisper_state changes · Updated 2023-03-26 17:09:06 +04:00    LLM-Inference	4392 3		ZIP  TAR.GZ
timing 4f074fb7a8 · tmp : demonstrate how to measure time of ggml ops · Updated 2023-03-09 11:28:06 +04:00    LLM-Inference	4403 1		ZIP  TAR.GZ
guided a0da7f71a2 · command : wip in progress, improve guided decoding · Updated 2023-02-19 21:39:05 +04:00    LLM-Inference	4419 1		ZIP  TAR.GZ
diarization ec44ad0a75 · diarization : try conv and self-attention embeddings · Updated 2023-02-19 15:00:12 +04:00    LLM-Inference	4420 4		ZIP  TAR.GZ
chess 59c997ca2d · wip ignore · Updated 2023-02-15 21:11:12 +04:00    LLM-Inference	4427 1		ZIP  TAR.GZ
arghh 7aa1174315 · bench : fix Windows linkage by moving ggml benches in whisper lib .. · Updated 2023-01-18 23:16:25 +04:00    LLM-Inference	4465 1		ZIP  TAR.GZ
fa-decoder e2aa556a99 · whisper : experiments with Flash Attention in the decoder · Updated 2023-01-07 23:00:51 +04:00    LLM-Inference	4487 1		ZIP  TAR.GZ
threads 4e6d2e98ab · ggml : try to improve threading · Updated 2022-12-29 15:05:20 +04:00    LLM-Inference	4527 1		ZIP  TAR.GZ
nvblas 683f111088 · ggml : initial tests with libnvblas · Updated 2022-12-09 00:01:52 +04:00    LLM-Inference	4606 1		ZIP  TAR.GZ
macros-cvt-fp16 e0bd97f41f · ggml : use macros to inline FP16 <-> FP32 conversions · Updated 2022-12-07 00:05:33 +04:00    LLM-Inference	4610 1		ZIP  TAR.GZ
stream 0a2621b637 · stream : add "max_tokens" cli arg · Updated 2022-11-20 23:22:02 +04:00    LLM-Inference	4688 5		ZIP  TAR.GZ