Georgi Gerganov
|
32866c5edd
editorconfig : fix whitespace and indentation #4710
|
2 лет назад |
minarchist
|
5d7002d437
server : add --override-kv parameter (#4710)
|
2 лет назад |
Nam D. Tran
|
26f3071d71
py : re-enable mmap in convert hf (#4732)
|
2 лет назад |
Daniel Bevenius
|
775ac8712a
finetune: fix typo in README.md (#4733)
|
2 лет назад |
Georgi Gerganov
|
58ba655af0
metal : enable shader debugging (cmake option) (#4705)
|
2 лет назад |
Someone Serge
|
edd1ab7bc3
flake.lock: update
|
2 лет назад |
Someone Serge
|
198ed7ebfc
flake.nix: suggest the binary caches
|
2 лет назад |
Someone Serge
|
d836174731
workflows: nix-ci: add a qemu job for jetsons
|
2 лет назад |
Someone Serge
|
06f2a5d190
workflows: nix-flakestry: drop tag filters
|
2 лет назад |
Someone Serge
|
c5239944ba
workflows: weekly `nix flake update`
|
2 лет назад |
Someone Serge
|
1e9ae54cf2
workflows: nix-ci: add a job for eval
|
2 лет назад |
Someone Serge
|
7adedecbe3
workflows: nix-ci: init; build flake outputs
|
2 лет назад |
Someone Serge
|
356ea17e0f
flake.nix: expose checks
|
2 лет назад |
Someone Serge
|
a5c088d8c6
flake.nix: rocm not yet supported on aarch64, so hide the output
|
2 лет назад |
Someone Serge
|
1e3900ebac
flake.nix: expose full scope in legacyPackages
|
2 лет назад |
Georgi Gerganov
|
e39106c055
ggml : add ggml_vdotq_s32 alias (#4715)
|
2 лет назад |
Georgi Gerganov
|
9fbda719de
clip : refactor + bug fixes (#4696)
|
2 лет назад |
Johannes Gäßler
|
39d8bc71ed
CUDA: fixed tensor cores not being used on RDNA3 (#4697)
|
2 лет назад |
automaticcat
|
24a447e20a
ggml : add ggml_cpu_has_avx_vnni() (#4589)
|
2 лет назад |
Johannes Gäßler
|
a20f3c7465
CUDA: fix tensor core logic for Pascal and HIP (#4682)
|
2 лет назад |
Georgi Gerganov
|
0235b9b571
clip : use ggml_backend_buffer_is_host (#4205)
|
2 лет назад |
Steward Garcia
|
ce18d727a4
clip : enable gpu backend (#4205)
|
2 лет назад |
hydai
|
91bb39cec7
cuda: fix vmm oom issue on NVIDIA AGX Orin (#4687)
|
2 лет назад |
crasm
|
04ac0607e9
python : add check-requirements.sh and GitHub workflow (#4585)
|
2 лет назад |
Philip Taron
|
68eccbdc5b
flake.nix : rewrite (#4605)
|
2 лет назад |
Cuong Trinh Manh
|
97bbca6e85
cmake : fix ld warning duplicate libraries libllama.a (#4671)
|
2 лет назад |
Justine Tunney
|
4af4801566
llava-cli : refactor to use sampling library (#4669)
|
2 лет назад |
Justine Tunney
|
db49ff8ed7
server : replace sleep with condition variables (#4673)
|
2 лет назад |
SakuraUmi
|
60f55e888c
server : fix OpenAI server sampling w.r.t. penalty. (#4675)
|
2 лет назад |
Karthik Sethuraman
|
b93edd22f5
server : allow to generate multimodal embeddings (#4681)
|
2 лет назад |