Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
gg/tmp-ci
5ddad95e
·
ci : tmp disable gguf-split
·
Apr 29, 2024
gg/bpe-preprocess
80cb3127
·
tests : disable test-tokenizer-1-bpe due to slowness
·
Apr 29, 2024
gg/fix-min-max
8c259f6f
·
ggml : fix MIN / MAX macros
·
Apr 25, 2024
gg/add-phi-3-support
5dcccb3a
·
convert : fix tokenizer conversion
·
Apr 23, 2024
test-bench
124e4dce
·
Update
·
Apr 22, 2024
gg/llama3-support
37507069
·
llama : add llama_token_is_eog()
·
Apr 20, 2024
gg/disable-sgemm
f02ea667
·
ggml : temporary disable llamafile sgemm until fixed
·
Apr 16, 2024
hp/tmp/kv-cache-defrag
eedd42e3
·
KV Cache defrag hash overflow - TMP Fix by @slaren
·
Apr 16, 2024
sl/hash-improvements
80d6c815
·
ggml : hash table improvements
·
Apr 15, 2024
gg/imatrix-remove-assert
8b495540
·
imatrix : remove invalid assert
·
Apr 12, 2024
gg/authors
072e0a4d
·
scipts : add LICENSE and gen-authors.sh to sync
·
Apr 09, 2024
ceb/bert-tokenizer-fixes
a37696d4
·
speculative : more robust tokenizer comparison
·
Apr 04, 2024
gg/flash-attn-a
4c190ba6
·
cuda : reduce registers
·
Mar 28, 2024
compilade/fix-command-r
64b7d858
·
llama : fix command-r inference
·
Mar 28, 2024
gg/flash-attn-wip
6be02b59
·
cuda : fix build
·
Mar 27, 2024
ceb/wpm-portable-tolower
87a6088f
·
rename unicodedata.{cpp,h} to unicode-data.{cpp,h}
·
Mar 26, 2024
ik/quantize_with_kv_overrides
9c5fd6be
·
minor : spacing
·
Mar 26, 2024
ik/test_quantize_fns
6f20e267
·
Include IQ2_XXS and IQ2_XS in teet-quantize-fns
·
Mar 25, 2024
sl/cuda-f16-fix3
210e4691
·
cuda : fix LLAMA_CUDA_F16 build
·
Mar 25, 2024
ceb/fix-win-unicode-fpaths
d05c13b3
·
llama : fix BPE LF token on MSVC
·
Mar 23, 2024
Prev
1
2
3
4
5
6
7
…
13
Next