ggml-org/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-19 18:45:26 +08:00
Code Issues Packages Projects Releases Wiki Activity
10,505 Commits 712 Branches 7,121 Tags

Default Branch

master

ee4c505a4f · server: add dedup-cache-models preset option (#27346) · Updated 2026-08-19 17:04:26 +08:00
 ZIP  TAR.GZ

Branches

ik/even_better_iq1s

5440a127c7 · iq1_s: fix dequantize on the CPU · Updated 2024-03-11 21:17:28 +08:00    tqcq

8102
6
 ZIP  TAR.GZ
gg/try-fix-sycl-iq1_s

76be02aebc · sycl : fix grid type · Updated 2024-03-11 21:17:08 +08:00    tqcq

8097
3
 ZIP  TAR.GZ
sycl_q3s_q1s

989e15b3c1 · Merge branch 'master' into sycl_q3s_q1s · Updated 2024-03-11 11:11:35 +08:00    tqcq

8104
9
 ZIP  TAR.GZ
gritlm-pr

b54afce9f4 · mostly style fixes; fix KQ_mask comment · Updated 2024-03-10 03:03:46 +08:00    tqcq

8147
10
 ZIP  TAR.GZ
gg/bert-f16

0ba20ed97a · llama : compute BERT graph with F16 K, V · Updated 2024-03-07 22:33:30 +08:00    tqcq

8137
1
 ZIP  TAR.GZ
revert-5901-fix_set_gpu

b5b0270372 · Revert "[SYCL] fix error when set main gpu to non-zero (#5901)" · Updated 2024-03-07 17:11:18 +08:00    tqcq

8141
1
 ZIP  TAR.GZ
ik/iq3_s_multiplier

31cecc8734 · iq3_s_mult_shuffle: use lookup table on Metal · Updated 2024-03-05 16:19:44 +08:00    tqcq

8215
24
 ZIP  TAR.GZ
gg/fix-embeddings-wip

4ec0e9abbf · wip · Updated 2024-03-04 23:07:12 +08:00    tqcq

8164
5
 ZIP  TAR.GZ
ci/server/fix-slow-test

eb0bf32caf · server: tests: schedule slow dispatch only on release or on demand · Updated 2024-03-03 06:18:31 +08:00    tqcq

8176
1
 ZIP  TAR.GZ
ceb/convert-hf-refactor

0b673ca187 · s/_MODEL_CLASSES/_model_classes/ · Updated 2024-03-03 01:14:37 +08:00    tqcq

8189
3
 ZIP  TAR.GZ
ik/iq3_s_faster

d4dfc250cc · Fix ARM_NEON · Updated 2024-03-02 16:12:02 +08:00    tqcq

8194
7
 ZIP  TAR.GZ
ceb/convert-vocab-fallback

f8ab539190 · convert : update help string · Updated 2024-03-02 01:29:34 +08:00    tqcq

8192
3
 ZIP  TAR.GZ
gg/fix-starcoder2

9862d59c05 · llama : change starcoder2 rope type · Updated 2024-03-01 21:10:31 +08:00    tqcq

8201
8
 ZIP  TAR.GZ
ik/i-quants-64

f0cbb6ddf6 · iq1_s: turn off SIMD implementation for QK_K = 64 (it does not work) · Updated 2024-02-28 14:28:10 +08:00    tqcq

8216
6
 ZIP  TAR.GZ
gg/kv-compress

14d757066b · llama : add llama_kv_cache_compress (EXPERIMENTAL) · Updated 2024-02-27 22:24:40 +08:00    tqcq

8217
1
 ZIP  TAR.GZ
gg/float-pos

608f449880 · swift : fix build · Updated 2024-02-24 01:02:09 +08:00    tqcq

8248
4
 ZIP  TAR.GZ
gg/py-minor-fixes

56c047156a · py : minor fixes · Updated 2024-02-23 01:22:56 +08:00    tqcq

8257
1
 ZIP  TAR.GZ
sl/fix-quant-kv-shift

5271c75666 · llama : fix K-shift with quantized K (wip) · Updated 2024-02-22 07:28:42 +08:00    tqcq

8265
1
 ZIP  TAR.GZ
gg/flash-attn-sync

f249c997a8 · llama : adapt to F16 KQ_pos · Updated 2024-02-19 19:31:02 +08:00    tqcq

8303
62
 ZIP  TAR.GZ
gg/metal-batched

412735ec70 · Merge branch 'master' into gg/metal-batched · Updated 2024-02-19 17:25:24 +08:00    tqcq

8303
6
 ZIP  TAR.GZ