upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-01 23:50:47 -05:00
Code Issues Packages Projects Releases Wiki Activity
10,223 Commits 645 Branches 6,962 Tags

Default Branch

master

11924d4c17 · test: fix some CI errors (#26415) · Updated 2026-08-01 17:16:29 -05:00
 ZIP  TAR.GZ

Branches

sl/cuda-f16-fix3

210e469114 · cuda : fix LLAMA_CUDA_F16 build · Updated 2024-03-25 09:31:10 -05:00    upstream-archive

7695
1
 ZIP  TAR.GZ
ceb/fix-win-unicode-fpaths

d05c13b3b9 · llama : fix BPE LF token on MSVC · Updated 2024-03-23 13:03:16 -05:00    upstream-archive

7715
3
 ZIP  TAR.GZ
gg/flash-attn-rebase

3a468e6f9f · llama : fix type of KQ_mask and KQ_pos · Updated 2024-03-22 10:12:17 -05:00    upstream-archive

7720
68
 ZIP  TAR.GZ
ik/quantize_not_repeating

0e826d12a5 · quantize: be able to specify the token embedding tensor type · Updated 2024-03-22 09:27:34 -05:00    upstream-archive

7729
2
 ZIP  TAR.GZ
gg/hf-args

8c3d5b5a79 · common : remove defaults · Updated 2024-03-22 08:33:24 -05:00    upstream-archive

7725
2
 ZIP  TAR.GZ
patch-1

12aa74ba7d · minor : spacing · Updated 2024-03-22 08:24:57 -05:00    upstream-archive

7950
6
 ZIP  TAR.GZ
gg/metal-dequant-align

072c56fcdb · metal : fix the fix · Updated 2024-03-22 02:58:22 -05:00    upstream-archive

7730
3
 ZIP  TAR.GZ
ik/try_fix_rocm_k_cache

a710d58d88 · Try fix quantized k-cache on ROCm · Updated 2024-03-21 13:18:50 -05:00    upstream-archive

7735
1
 ZIP  TAR.GZ
ik/fix_k_cache_backend_tests

68e4fed4d9 · Now fix test-quantize-fns · Updated 2024-03-21 06:18:03 -05:00    upstream-archive

7742
3
 ZIP  TAR.GZ
compilade/fix-server-tests-penalty

9a424a3872 · server : fix tests expecting old repeat penalty · Updated 2024-03-19 16:12:28 -05:00    upstream-archive

7758
1
 ZIP  TAR.GZ
gg/repeng

0a9bc301ac · control-vectors : minor code style updates · Updated 2024-03-14 09:43:37 -05:00    upstream-archive

7797
3
 ZIP  TAR.GZ
gg/metal-embed

abf0afd0d6 · ci : fix iOS builds to use embedded library · Updated 2024-03-14 04:34:22 -05:00    upstream-archive

7815
4
 ZIP  TAR.GZ
ik/try_fix_iq1s_sycl

9f805264dc · Attempt 2 · Updated 2024-03-12 11:40:13 -05:00    upstream-archive

7815
3
 ZIP  TAR.GZ
ik/even_better_iq1s

5440a127c7 · iq1_s: fix dequantize on the CPU · Updated 2024-03-11 08:17:28 -05:00    upstream-archive

7828
6
 ZIP  TAR.GZ
gg/try-fix-sycl-iq1_s

76be02aebc · sycl : fix grid type · Updated 2024-03-11 08:17:08 -05:00    upstream-archive

7823
3
 ZIP  TAR.GZ
sycl_q3s_q1s

989e15b3c1 · Merge branch 'master' into sycl_q3s_q1s · Updated 2024-03-10 22:11:35 -05:00    upstream-archive

7830
9
 ZIP  TAR.GZ
gritlm-pr

b54afce9f4 · mostly style fixes; fix KQ_mask comment · Updated 2024-03-09 13:03:46 -06:00    upstream-archive

7873
10
 ZIP  TAR.GZ
gg/bert-f16

0ba20ed97a · llama : compute BERT graph with F16 K, V · Updated 2024-03-07 08:33:30 -06:00    upstream-archive

7863
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 03:11:18 -06:00    upstream-archive

7867
1
 ZIP  TAR.GZ
ik/iq3_s_multiplier

31cecc8734 · iq3_s_mult_shuffle: use lookup table on Metal · Updated 2024-03-05 02:19:44 -06:00    upstream-archive

7941
24
 ZIP  TAR.GZ