Default Branch

30c5194c96 · ruby : null-check (#3689) · Updated 2026-03-05 06:36:42 +01:00

Branches

9c1a414feb · use secrets.GPG_PRIVATE_KEY and GPG_PASSPHRASE · Updated 2023-09-09 16:49:13 +02:00

3338
5

3efe146d27 · ci : enable java package publishing · Updated 2023-08-30 21:13:38 +02:00

3360
1

8cbc363561 · coreml : attempt to fix ANE-optimized models · Updated 2023-07-11 22:03:53 +02:00

3398
1

c6174cb868 · wip · Updated 2023-05-02 20:47:12 +02:00

3466
1

c456ca476b · llama podcast · Updated 2023-04-01 12:13:27 +02:00

3534
1

3627ef51f6 · minor · Updated 2023-03-26 22:54:52 +02:00

3551
7

0244810697 · rebase on master after whisper_state changes · Updated 2023-03-26 15:09:06 +02:00

3551
3

4f074fb7a8 · tmp : demonstrate how to measure time of ggml ops · Updated 2023-03-09 08:28:06 +01:00

3562
1

a0da7f71a2 · command : wip in progress, improve guided decoding · Updated 2023-02-19 18:39:05 +01:00

3578
1

ec44ad0a75 · diarization : try conv and self-attention embeddings · Updated 2023-02-19 12:00:12 +01:00

3579
4

59c997ca2d · wip ignore · Updated 2023-02-15 18:11:12 +01:00

3586
1

7aa1174315 · bench : fix Windows linkage by moving ggml benches in whisper lib .. · Updated 2023-01-18 20:16:25 +01:00

3624
1

e2aa556a99 · whisper : experiments with Flash Attention in the decoder · Updated 2023-01-07 20:00:51 +01:00

3646
1

4e6d2e98ab · ggml : try to improve threading · Updated 2022-12-29 12:05:20 +01:00

3686
1

683f111088 · ggml : initial tests with libnvblas · Updated 2022-12-08 21:01:52 +01:00

3765
1

e0bd97f41f · ggml : use macros to inline FP16 <-> FP32 conversions · Updated 2022-12-06 21:05:33 +01:00

3769
1

0a2621b637 · stream : add "max_tokens" cli arg · Updated 2022-11-20 20:22:02 +01:00

3847
5

fa9621e5e9 · mtl : update Makefile to support Metal · Updated 2022-11-12 07:32:03 +01:00

3857
2

5d895d60b6 · Merge branch 'master' into avx512 · Updated 2022-11-06 08:09:50 +01:00

3862
7

210a6fb83c · wip : some unsuccessful experiments using DP · Updated 2022-11-01 20:28:30 +01:00

3885
1