Default Branch

1fe009caed · talk-llama : fix build (#0) · Updated 2026-08-14 21:16:06 +02:00

Branches

3ac0558009 · ios : update SPM package · Updated 2023-09-15 11:13:33 +02:00    public_git

4212
44

09a6325de5 · ggml : use sched_yield when using BLAS + add comment · Updated 2023-09-12 12:33:09 +02:00    public_git

4213
2

3c50be2217 · whisper : remove comment · Updated 2023-09-10 12:27:06 +02:00    public_git

4230
9

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

4215
5

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

4237
1

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

4275
1

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

4343
1

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

4411
1

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

4428
7

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

4428
3

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

4439
1

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

4455
1

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

4456
4

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

4463
1

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

4501
1

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

4523
1

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

4563
1

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

4642
1

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

4646
1

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

4724
5