happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
7,562 Commits 517 Branches 5,142 Tags 1 GiB

Default Branch

master

07a0c4ba92 · Revert "ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413)" (#18426) · Updated 2025-12-28 04:53:36 -08:00
 ZIP  TAR.GZ

Branches

gg/llama3-support

3750706962 · llama : add llama_token_is_eog() · Updated 2024-04-20 06:52:03 -07:00
4868
4
 ZIP  TAR.GZ
gg/disable-sgemm

f02ea667c1 · ggml : temporary disable llamafile sgemm until fixed · Updated 2024-04-16 12:45:56 -07:00
4877
1
 ZIP  TAR.GZ
hp/tmp/kv-cache-defrag

eedd42e376 · KV Cache defrag hash overflow - TMP Fix by @slaren · Updated 2024-04-16 01:24:34 -07:00
4880
1
 ZIP  TAR.GZ
gg/imatrix-remove-assert

8b495540fa · imatrix : remove invalid assert · Updated 2024-04-12 01:45:12 -07:00    happyz

4905
1
 ZIP  TAR.GZ
gg/authors

072e0a4d3b · scipts : add LICENSE and gen-authors.sh to sync · Updated 2024-04-08 23:19:33 -07:00    happyz

4981
3
 ZIP  TAR.GZ
ceb/bert-tokenizer-fixes

a37696d4f1 · speculative : more robust tokenizer comparison · Updated 2024-04-04 15:28:13 -07:00    happyz

4951
9
 ZIP  TAR.GZ
gg/flash-attn-a

4c190ba676 · cuda : reduce registers · Updated 2024-03-28 12:17:08 -07:00    happyz

4993
77
 ZIP  TAR.GZ
compilade/fix-command-r

64b7d85891 · llama : fix command-r inference · Updated 2024-03-28 03:22:24 -07:00    happyz

4998
1
 ZIP  TAR.GZ
gg/flash-attn-wip

6be02b5969 · cuda : fix build · Updated 2024-03-27 01:31:52 -07:00    happyz

5015
72
 ZIP  TAR.GZ
ceb/wpm-portable-tolower

87a6088ffe · rename unicodedata.{cpp,h} to unicode-data.{cpp,h} · Updated 2024-03-26 07:52:33 -07:00    happyz

5030
7
 ZIP  TAR.GZ
ik/quantize_with_kv_overrides

9c5fd6be14 · minor : spacing · Updated 2024-03-26 05:09:02 -07:00    happyz

5028
2
 ZIP  TAR.GZ
ik/test_quantize_fns

6f20e2672f · Include IQ2_XXS and IQ2_XS in teet-quantize-fns · Updated 2024-03-25 10:01:20 -07:00    happyz

5032
1
 ZIP  TAR.GZ
sl/cuda-f16-fix3

210e469114 · cuda : fix LLAMA_CUDA_F16 build · Updated 2024-03-25 07:31:10 -07:00    happyz

5034
1
 ZIP  TAR.GZ
ceb/fix-win-unicode-fpaths

d05c13b3b9 · llama : fix BPE LF token on MSVC · Updated 2024-03-23 11:03:16 -07:00    happyz

5054
3
 ZIP  TAR.GZ
gg/flash-attn-rebase

3a468e6f9f · llama : fix type of KQ_mask and KQ_pos · Updated 2024-03-22 08:12:17 -07:00    happyz

5059
68
 ZIP  TAR.GZ
ik/quantize_not_repeating

0e826d12a5 · quantize: be able to specify the token embedding tensor type · Updated 2024-03-22 07:27:34 -07:00    happyz

5068
2
 ZIP  TAR.GZ
gg/hf-args

8c3d5b5a79 · common : remove defaults · Updated 2024-03-22 06:33:24 -07:00    happyz

5064
2
 ZIP  TAR.GZ
patch-1

12aa74ba7d · minor : spacing · Updated 2024-03-22 06:24:57 -07:00    happyz

5289
6
 ZIP  TAR.GZ
gg/metal-dequant-align

072c56fcdb · metal : fix the fix · Updated 2024-03-22 00:58:22 -07:00    happyz

5069
3
 ZIP  TAR.GZ
ik/try_fix_rocm_k_cache

a710d58d88 · Try fix quantized k-cache on ROCm · Updated 2024-03-21 11:18:50 -07:00    happyz

5074
1
 ZIP  TAR.GZ