Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
ik/iq3_s_multiplier
31cecc87
·
iq3_s_mult_shuffle: use lookup table on Metal
·
Mar 05, 2024
gg/fix-embeddings-wip
4ec0e9ab
·
wip
·
Mar 04, 2024
ci/server/fix-slow-test
eb0bf32c
·
server: tests: schedule slow dispatch only on release or on demand
·
Mar 02, 2024
ceb/convert-hf-refactor
0b673ca1
·
s/_MODEL_CLASSES/_model_classes/
·
Mar 02, 2024
ik/iq3_s_faster
d4dfc250
·
Fix ARM_NEON
·
Mar 02, 2024
ceb/convert-vocab-fallback
f8ab5391
·
convert : update help string
·
Mar 01, 2024
gg/fix-starcoder2
9862d59c
·
llama : change starcoder2 rope type
·
Mar 01, 2024
ik/i-quants-64
f0cbb6dd
·
iq1_s: turn off SIMD implementation for QK_K = 64 (it does not work)
·
Feb 28, 2024
gg/kv-compress
14d75706
·
llama : add llama_kv_cache_compress (EXPERIMENTAL)
·
Feb 27, 2024
gg/float-pos
608f4498
·
swift : fix build
·
Feb 23, 2024
gg/py-minor-fixes
56c04715
·
py : minor fixes
·
Feb 22, 2024
sl/fix-quant-kv-shift
5271c756
·
llama : fix K-shift with quantized K (wip)
·
Feb 22, 2024
gg/flash-attn-sync
f249c997
·
llama : adapt to F16 KQ_pos
·
Feb 19, 2024
gg/metal-batched
412735ec
·
Merge branch 'master' into gg/metal-batched
·
Feb 19, 2024
gg/rename-n_ctx
47c662b0
·
fix some spaces added by IDE in math op
·
Feb 18, 2024
gg/fix-android
974e3cad
·
ggml : try another fix
·
Feb 17, 2024
gg/hf
e856bfed
·
hf : add support for --repo and --file
·
Feb 15, 2024
ceb/nomic-bert
ccd757a1
·
convert : fix mistakes from refactoring
·
Feb 13, 2024
ik/iq1_s
5c977221
·
iq1_s: slightly faster dot product
·
Feb 13, 2024
ik/fix_warnings
4246b71a
·
Fix compiler warnings (shadow variable)
·
Feb 13, 2024
Prev
1
2
3
4
5
6
7
8
9
…
13
Next