upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-30 01:47:39 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,280 Commits 827 Branches 7,666 Tags

Default Branch

master

2a53ace3be · SYCL: reduce tensor allreduce sync with pinned host buffers (#29604) · Updated 2026-09-30 01:25:13 -05:00
 ZIP  TAR.GZ

Branches

sl/dump-allocs

cad8abb49b · add tool to allow plotting tensor allocation maps within buffers · Updated 2024-08-06 15:09:51 -05:00    upstream-archive

7747
1
 ZIP  TAR.GZ
prepare-PR-of-minicpm-v2.5-gg

6e299132e7 · clip : style changes · Updated 2024-08-06 03:44:29 -05:00    upstream-archive

8071
56
 ZIP  TAR.GZ
gg/replace-all

bddcc5f985 · llama : better replace_all · Updated 2024-08-04 05:42:08 -05:00    upstream-archive

7772
1
 ZIP  TAR.GZ
compilade/gguf-py-quants-class

229c35cb59 · gguf-py : remove LlamaFileTypeMap · Updated 2024-08-03 20:22:37 -05:00    upstream-archive

7775
5
 ZIP  TAR.GZ
codeplay/sycl-main

eab4a88210 · Using dp4a ptx intrinsics for an improved Mul8MAT perf [By Alcpz] · Updated 2024-07-29 10:52:29 -05:00    upstream-archive

7793
1
 ZIP  TAR.GZ
compilade/refactor-session-files

9cddd9aeec · llama : cast seq_id in comparison with unsigned n_seq_max · Updated 2024-07-27 14:50:23 -05:00    upstream-archive

7831
7
 ZIP  TAR.GZ
sycl-conv-op

9aeb0e1f75 · sycl add conv support · Updated 2024-07-25 07:15:02 -05:00    upstream-archive

7820
1
 ZIP  TAR.GZ
gg/system-info-llamafile

5934580905 · ggml : add and use ggml_cpu_has_llamafile() · Updated 2024-07-24 03:31:41 -05:00    upstream-archive

7831
1
 ZIP  TAR.GZ
gg/llama-reorganize

fe28a7b9d8 · llama : clean-up · Updated 2024-07-23 00:38:50 -05:00    upstream-archive

7839
11
 ZIP  TAR.GZ
gg/allow-kv-overrides

57349e1db3 · llama : allow overrides for tokenizer flags · Updated 2024-07-21 06:42:15 -05:00    upstream-archive

7849
1
 ZIP  TAR.GZ
compilade/fix-metadata-name-extraction

1932a1b871 · gguf-py : do not use title case for naming convention · Updated 2024-07-20 15:55:06 -05:00    upstream-archive

7857
5
 ZIP  TAR.GZ
0cc4m/vulkan-fix-mm-tests

c8ee1bccdd · Fix Vulkan matmul tests compile errors · Updated 2024-07-20 01:01:18 -05:00    upstream-archive

7857
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 21:46:35 -05:00    upstream-archive

7857
2
 ZIP  TAR.GZ
gg/gguf-fix-null-defer

38061254b9 · gguf : handle null name during init · Updated 2024-07-19 05:45:00 -05:00    upstream-archive

7862
1
 ZIP  TAR.GZ
gg/quantize-fallback

f6ea7a093c · llama : change fallback type IQ4_NL -> Q4_0 · Updated 2024-07-16 02:00:57 -05:00    upstream-archive

7878
1
 ZIP  TAR.GZ
compilade/faster-lazy-safetensors

b971122eb1 · convert_hf : fix memory leak in lazy MoE conversion · Updated 2024-07-15 20:11:44 -05:00    upstream-archive

7880
3
 ZIP  TAR.GZ
compilade/fix-pydantic-example

f89eaa921e · pydantic : fix Python 3.9 and 3.10 support · Updated 2024-07-13 20:52:45 -05:00    upstream-archive

7894
2
 ZIP  TAR.GZ
compilade/fix-mpt-pretok

59ce85318a · test-tokenizer-random : reduce potential confilcts with #8379 · Updated 2024-07-13 00:56:05 -05:00    upstream-archive

7912
14
 ZIP  TAR.GZ
compilade/tokenize-example-parse-special

ba06b2deb7 · tokenize : add --no-parse-special option · Updated 2024-07-10 17:06:25 -05:00    upstream-archive

7912
1
 ZIP  TAR.GZ
gg/fix-python-names

117f7adbd9 · ggml : remove K_QUANTS_PER_ITERATION (#8306) · Updated 2024-07-10 07:23:12 -05:00    upstream-archive

7975
7
 ZIP  TAR.GZ