kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-07 03:30:23 +00:00
Code Issues Packages Projects Releases Wiki Activity
9,893 Commits 613 Branches 6,735 Tags

Default Branch

master

6f8895feec · opencl: general flash attention decode performance optimizations (#25366) · Updated 2026-07-07 02:57:52 +00:00
 ZIP  TAR.GZ

Branches

ik/try_fix_iq1s_sycl

9f805264dc · Attempt 2 · Updated 2024-03-12 16:40:13 +00:00    kanshan

7485
3
 ZIP  TAR.GZ
ik/even_better_iq1s

5440a127c7 · iq1_s: fix dequantize on the CPU · Updated 2024-03-11 13:17:28 +00:00    kanshan

7498
6
 ZIP  TAR.GZ
gg/try-fix-sycl-iq1_s

76be02aebc · sycl : fix grid type · Updated 2024-03-11 13:17:08 +00:00    kanshan

7493
3
 ZIP  TAR.GZ
sycl_q3s_q1s

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

7500
9
 ZIP  TAR.GZ
gritlm-pr

b54afce9f4 · mostly style fixes; fix KQ_mask comment · Updated 2024-03-09 19:03:46 +00:00    kanshan

7543
10
 ZIP  TAR.GZ
gg/bert-f16

0ba20ed97a · llama : compute BERT graph with F16 K, V · Updated 2024-03-07 14:33:30 +00:00    kanshan

7533
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 09:11:18 +00:00    kanshan

7537
1
 ZIP  TAR.GZ
ik/iq3_s_multiplier

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

7611
24
 ZIP  TAR.GZ
gg/fix-embeddings-wip

4ec0e9abbf · wip · Updated 2024-03-04 15:07:12 +00:00    kanshan

7560
5
 ZIP  TAR.GZ
ci/server/fix-slow-test

eb0bf32caf · server: tests: schedule slow dispatch only on release or on demand · Updated 2024-03-02 22:18:31 +00:00    kanshan

7572
1
 ZIP  TAR.GZ
ceb/convert-hf-refactor

0b673ca187 · s/_MODEL_CLASSES/_model_classes/ · Updated 2024-03-02 17:14:37 +00:00    kanshan

7585
3
 ZIP  TAR.GZ
ik/iq3_s_faster

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

7590
7
 ZIP  TAR.GZ
ceb/convert-vocab-fallback

f8ab539190 · convert : update help string · Updated 2024-03-01 17:29:34 +00:00    kanshan

7588
3
 ZIP  TAR.GZ
gg/fix-starcoder2

9862d59c05 · llama : change starcoder2 rope type · Updated 2024-03-01 13:10:31 +00:00    kanshan

7597
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 06:28:10 +00:00    kanshan

7612
6
 ZIP  TAR.GZ
gg/kv-compress

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

7613
1
 ZIP  TAR.GZ
gg/float-pos

608f449880 · swift : fix build · Updated 2024-02-23 17:02:09 +00:00    kanshan

7644
4
 ZIP  TAR.GZ
gg/py-minor-fixes

56c047156a · py : minor fixes · Updated 2024-02-22 17:22:56 +00:00    kanshan

7653
1
 ZIP  TAR.GZ
sl/fix-quant-kv-shift

5271c75666 · llama : fix K-shift with quantized K (wip) · Updated 2024-02-21 23:28:42 +00:00    kanshan

7661
1
 ZIP  TAR.GZ
gg/flash-attn-sync

f249c997a8 · llama : adapt to F16 KQ_pos · Updated 2024-02-19 11:31:02 +00:00    kanshan

7699
62
 ZIP  TAR.GZ