Default Branch

fc674574ca · bench : sync submit-results URL to ggml-org (#3769) · Updated 2026-04-20 07:12:57 +02:00

Branches

13c5446759 · Update ggml-cuda/mmvq.cu · Updated 2024-06-11 16:37:32 +02:00    public_git

2907
2

059bcd3009 · ci : fix CUDA builds · Updated 2024-06-11 10:40:19 +02:00    public_git

2907
1

ba69578828 · whisper : add whisper_token_count helper · Updated 2024-03-25 13:46:07 +01:00    public_git

3051
2

66df44b0b7 · alloc : fix allocation data of pre-allocated leafs · Updated 2024-03-16 15:47:14 +01:00    public_git

3060
2

f25edade2b · whisper : alternative way to handle the external encoders · Updated 2024-02-12 15:32:26 +01:00    public_git

3187
2

15c4fdce45 · chess : tuning performance · Updated 2023-11-30 09:50:47 +01:00    public_git

3417
21

4260d4fc70 · wchess : minor · Updated 2023-11-28 14:10:18 +01:00    public_git

3417
11

c8b3bc6a0d · cuda : use CUBLAS_COMPTE_F32 insted of CUBLAS_COMPUTE_F16 · Updated 2023-11-27 10:57:07 +01:00    public_git

3399
1

ee2971bf6a · bench : multi-thread memcpy · Updated 2023-11-21 20:57:07 +01:00    public_git

3417
1

ec96d68402 · whisper : quantize encoder only · Updated 2023-11-16 15:19:02 +01:00    public_git

3427
1

270b1e48db · cuda : sync llama.cpp fixes · Updated 2023-11-15 14:52:06 +01:00    public_git

3439
14

5031f54717 · whisper : try to fix the parallel whisper_state functionality (#1479) · Updated 2023-11-12 13:52:38 +01:00    public_git

3447
21

a2f3b82db3 · whisper : free backend instances in whisper_state · Updated 2023-11-12 13:31:51 +01:00    public_git

3447
23

7a91a3ba60 · bench-all : add q4 models · Updated 2023-11-10 21:23:18 +01:00    public_git

3447
16

bf4110dbcf · whisper : wip sched (not working yet) · Updated 2023-11-09 18:07:54 +01:00    public_git

3452
2

40be74271f · models : update readme · Updated 2023-11-07 12:53:01 +01:00    public_git

3458
4

aaa3b5e5f6 · ggml : try to fix the abort mechanism · Updated 2023-11-05 19:02:24 +01:00    public_git

3465
1

673c55c683 · whisper : print log when using distilled models · Updated 2023-11-05 18:43:04 +01:00    public_git

3468
2

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

3497
44

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

3498
2