happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
7,565 Commits 518 Branches 5,144 Tags 1 GiB

Default Branch

master

382808c14b · ci : re-enable rocm build on amd64 (#18439) · Updated 2025-12-28 15:29:23 -08:00
 ZIP  TAR.GZ

Branches

gg/allow-kv-overrides

57349e1db3 · llama : allow overrides for tokenizer flags · Updated 2024-07-21 04:42:15 -07:00
4134
1
 ZIP  TAR.GZ
compilade/fix-metadata-name-extraction

1932a1b871 · gguf-py : do not use title case for naming convention · Updated 2024-07-20 13:55:06 -07:00
4142
5
 ZIP  TAR.GZ
0cc4m/vulkan-fix-mm-tests

c8ee1bccdd · Fix Vulkan matmul tests compile errors · Updated 2024-07-19 23:01:18 -07:00
4142
1
 ZIP  TAR.GZ
compilade/fix-convert-gemma-1-instruct

50d1a035f0 · convert_hf : fix Gemma v1 not setting BOS and EOS tokens · Updated 2024-07-19 19:46:35 -07:00
4142
2
 ZIP  TAR.GZ
gg/gguf-fix-null-defer

38061254b9 · gguf : handle null name during init · Updated 2024-07-19 03:45:00 -07:00
4147
1
 ZIP  TAR.GZ
gg/quantize-fallback

f6ea7a093c · llama : change fallback type IQ4_NL -> Q4_0 · Updated 2024-07-16 00:00:57 -07:00
4163
1
 ZIP  TAR.GZ
compilade/faster-lazy-safetensors

b971122eb1 · convert_hf : fix memory leak in lazy MoE conversion · Updated 2024-07-15 18:11:44 -07:00
4165
3
 ZIP  TAR.GZ
compilade/fix-pydantic-example

f89eaa921e · pydantic : fix Python 3.9 and 3.10 support · Updated 2024-07-13 18:52:45 -07:00
4179
2
 ZIP  TAR.GZ
compilade/fix-mpt-pretok

59ce85318a · test-tokenizer-random : reduce potential confilcts with #8379 · Updated 2024-07-12 22:56:05 -07:00
4197
14
 ZIP  TAR.GZ
compilade/tokenize-example-parse-special

ba06b2deb7 · tokenize : add --no-parse-special option · Updated 2024-07-10 15:06:25 -07:00
4197
1
 ZIP  TAR.GZ
gg/fix-python-names

117f7adbd9 · ggml : remove K_QUANTS_PER_ITERATION (#8306) · Updated 2024-07-10 05:23:12 -07:00
4260
7
 ZIP  TAR.GZ
compilade/gguf-py-fix-old-numpy

aaf7bc89e4 · Merge branch 'master' into compilade/gguf-py-fix-old-numpy · Updated 2024-07-08 21:10:06 -07:00
4215
2
 ZIP  TAR.GZ
compilade/pyright-tests

86ccd30983 · ci : only show warnings and errors in python type-check · Updated 2024-07-07 11:10:42 -07:00
4230
10
 ZIP  TAR.GZ
compilade/requirements-cpu-torch

a44f22e7d3 · py : use cpu-only torch in requirements.txt · Updated 2024-07-06 08:18:03 -07:00
4240
1
 ZIP  TAR.GZ
gg/indent

f55b647300 · llama : minor indentation during tensor loading · Updated 2024-07-04 09:34:04 -07:00
4262
16
 ZIP  TAR.GZ
sl/fix-ppl-seq-max

dcab343f2f · use 1 seq for kl_divergence · Updated 2024-07-03 07:22:58 -07:00
4277
2
 ZIP  TAR.GZ
fairydreaming/t5-clean-3-gg

703764a382 · convert : use non-fast T5 tokenizer · Updated 2024-07-02 09:29:26 -07:00
4319
10
 ZIP  TAR.GZ
gg/nix-remove-opencl

d4a1923d4e · minor : remove parentheses · Updated 2024-07-01 04:45:55 -07:00
4297
2
 ZIP  TAR.GZ
add-gemma2-soft-capping

51f0bd50a1 · Remove custom pre attention scaling and use computed value instead. · Updated 2024-06-29 20:02:50 -07:00
4300
10
 ZIP  TAR.GZ
codeplay/tg-warmup

712e4d9450 · Generate full token count during warm up · Updated 2024-06-28 05:29:00 -07:00
4303
1
 ZIP  TAR.GZ