Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/ggerganov/llama.cpp
. Pull mirroring updated
Sep 20, 2024
.
gg/fix-detokenization-added-tokens
f6185f9b
·
Fix detokenization of non-special added-tokens
·
Jan 13, 2024
gg/server-system-cache-4902
9ec53ba0
·
server : fix prompt caching with system prompt
·
Jan 13, 2024
gg/add-phixtral
9998ecd1
·
llama : add phixtral support (wip)
·
Jan 13, 2024
gg/update-phi2-convert
1fb563eb
·
py : try to fix flake stuff
·
Jan 13, 2024
ik/MoE_quant_mix
f5205f85
·
Make Q3_K_S be the same as olf Q3_K_L for Mixtral-8x7B
·
Jan 13, 2024
ik/quantize-iq2
f342143e
·
imatrix: guard even more against low-bit quantization misuse
·
Jan 12, 2024
gg/metal-feature-set
5d33d3cd
·
Merge branch 'master' into gg/metal-feature-set
·
Jan 12, 2024
gg/llama-fix-k-shift-n-rot
0cb764e4
·
llama : always use hparams.n_rot for ggml_rope_custom
·
Jan 12, 2024
ik/restore_k-quants_for_MoE
31fb4d8e
·
Merge branch 'master' into ik/restore_k-quants_for_MoE
·
Jan 11, 2024
ik/iq2_2.31bpw
9bfcb16f
·
Add llama enum for IQ2_XS
·
Jan 11, 2024
gg/spm-fix
f35acb84
·
swift : pin ggml commit + remove ggml.h from spm-headers
·
Jan 11, 2024
ik/imatrix
f0b71d5d
·
Cleanup
·
Jan 10, 2024
sl/backend-sched-page-align
2063b868
·
metal : page align the data ptr
·
Jan 10, 2024
gg/metal-ci-fixes
ef8ba127
·
metal : improve dequantize precision to match CPU
·
Jan 09, 2024
gg/server-infill-empty-prompt-4027
24096933
·
server : try to fix infill when prompt is empty
·
Jan 09, 2024
gg/fix-vld1q_s8_x4-4872
7216af5c
·
ggml : fix 32-bit ARM compat (cont)
·
Jan 09, 2024
gg/exclude-resources-spm
4aa73e37
·
swift : exclude ggml-metal.metal from the package
·
Jan 08, 2024
passkey
d57cb9c2
·
passkey : add readme
·
Jan 08, 2024
gg/self-extend-part-2
ea129218
·
main : add Self-Extend support
·
Jan 07, 2024
gg/self-extend
f33a8106
·
passkey : add comment
·
Jan 07, 2024
Prev
1
…
6
7
8
9
10
11
12
13
14
…
26
Next