LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity
10,397 Commits 684 Branches 7,066 Tags

Default Branch

master

84e908c625 · ci: fix thread sanitizer + remove ccache (#26927) · Updated 2026-08-12 20:01:12 +04:00
 ZIP  TAR.GZ

Branches

test-mac-os-ci

f46db27ea0 · ci : disable FMA on Mac OS · Updated 2023-07-05 19:29:08 +04:00    LLM-Inference

9612
5
 ZIP  TAR.GZ
try-fix-metal

5cc672a9a5 · metal : try to utilize more of the shared memory using smaller views · Updated 2023-06-26 23:23:04 +04:00    LLM-Inference

9649
1
 ZIP  TAR.GZ
avoid-gnu-source

78fafcaf10 · ggml : do not use _GNU_SOURCE gratuitously · Updated 2023-06-25 18:21:02 +04:00    LLM-Inference

9657
1
 ZIP  TAR.GZ
fix_clblast

20054a38c1 · Fix directory name · Updated 2023-05-27 03:00:08 +04:00    LLM-Inference

9807
1
 ZIP  TAR.GZ
chunks

a1cdd29cd2 · ggml : rms_norm in chunks · Updated 2023-05-20 11:15:54 +04:00    LLM-Inference

9828
2
 ZIP  TAR.GZ
steering

95dc4d7270 · Merge 'origin/master' into steering · Updated 2023-05-20 00:19:57 +04:00    LLM-Inference

9830
9
 ZIP  TAR.GZ
f16c

40ec4882c4 · ggml : use F16C conversion when available · Updated 2023-05-17 21:05:51 +04:00    LLM-Inference

9839
1
 ZIP  TAR.GZ
dequantize-matmul-3-gg

a3e6d62283 · cuda : alternative q4_q8 kernel · Updated 2023-05-12 18:02:39 +04:00    LLM-Inference

9873
8
 ZIP  TAR.GZ
remove-vzip

e116eb638c · ggml : speed-up Q5_0 + Q5_1 at 4 threads · Updated 2023-05-11 19:51:56 +04:00    LLM-Inference

9875
20
 ZIP  TAR.GZ
jed/spm-clblast

4baa85633a · Fix build · Updated 2023-05-07 05:44:07 +04:00    LLM-Inference

9883
5
 ZIP  TAR.GZ
ci_cublas

31ff9e2e83 · ci : add cublas to windows release · Updated 2023-05-04 01:21:20 +04:00    LLM-Inference

9898
1
 ZIP  TAR.GZ
q4_3-range-fix

102cd98074 · ggml : Q4_3c using 2x "Full range" approach · Updated 2023-04-23 15:56:44 +04:00    LLM-Inference

9979
8
 ZIP  TAR.GZ
q4_0-q4_2-range-fix

71e6ae3779 · ggml : continue from #729 (wip) · Updated 2023-04-22 19:49:07 +04:00    LLM-Inference

9979
7
 ZIP  TAR.GZ
gg/rmse_quantization

a0242a833c · Minor, plus rebase on master · Updated 2023-04-22 18:07:10 +04:00    LLM-Inference

9979
2
 ZIP  TAR.GZ
quant-attn

4b8d5e3890 · llama : quantize attention results · Updated 2023-04-22 12:35:13 +04:00    LLM-Inference

9984
1
 ZIP  TAR.GZ
mmap-pages-stats

1506737499 · Add mmap pages stats (disabled by default) · Updated 2023-04-16 20:22:30 +04:00    LLM-Inference

10034
1
 ZIP  TAR.GZ
flash-attn

36ddd12924 · llama : add flash attention (demo) · Updated 2023-04-05 23:12:04 +04:00    LLM-Inference

10100
1
 ZIP  TAR.GZ
mmap

c9c820ff36 · Added support for _POSIX_MAPPED_FILES if defined in source (#564) · Updated 2023-03-29 01:26:25 +04:00    LLM-Inference

10334
8
 ZIP  TAR.GZ
q4_1_more_accel

4aeee216fd · Regroup q4_1 dot addition for better numerics. · Updated 2023-03-25 00:20:57 +04:00    LLM-Inference

10215
2
 ZIP  TAR.GZ
q4_1_more_accel_kahan

66ea164e1d · Kahan summation on Q4_1 · Updated 2023-03-23 07:28:51 +04:00    LLM-Inference

10242
2
 ZIP  TAR.GZ