 Lars Grammel
|
b7e7982953
readme : add lgrammel/modelfusion JS/TS client for llama.cpp (#4814)
|
il y a 2 ans |
 slaren
|
226460cc0d
llama-bench : add no-kv-offload parameter (#4812)
|
il y a 2 ans |
 Johannes Gäßler
|
d5a410e855
CUDA: fixed redundant value dequantization (#4809)
|
il y a 2 ans |
 Georgi Gerganov
|
9dede37d81
llama : remove unused vars (#4796)
|
il y a 2 ans |
|
Georgi Gerganov
|
3c36213df8
llama : remove redundant GQA check (#4796)
|
il y a 2 ans |
 Alex Azarov
|
72d8407b36
llama.swiftui : use llama.cpp as SPM package (#4804)
|
il y a 2 ans |
|
Georgi Gerganov
|
d117d4dc5d
llama : print tensor meta for debugging
|
il y a 2 ans |
|
Alex Azarov
|
3418c03ecc
llama.swiftui : add visionOS target (#4805)
|
il y a 2 ans |
 Konstantin Zhuravlyov
|
63ee677efd
ggml : use __builtin_amdgcn_sudot4 in __dp4a for gfx11 (#4787)
|
il y a 2 ans |
|
Georgi Gerganov
|
67984921a7
server : fix n_predict check (#4798)
|
il y a 2 ans |
 Daniel Illescas Romero
|
c75ca5d96f
llama.swiftui : use correct pointer for llama_token_eos (#4797)
|
il y a 2 ans |
|
Georgi Gerganov
|
96e80dabc6
examples : improve base-translate.sh script (#4783)
|
il y a 2 ans |
 a-n-n-a-l-e-e
|
eec22a1c63
cmake : check for openblas64 (#4134)
|
il y a 2 ans |
 Ikko Eltociear Ashimine
|
be36bb946a
flake.nix : fix typo (#4700)
|
il y a 2 ans |
|
Georgi Gerganov
|
91d38876df
metal : switch back to default.metallib (ggml/681)
|
il y a 2 ans |
|
Georgi Gerganov
|
d061bf9405
ggml : fix q2_k bpw in comments (ggml/680)
|
il y a 2 ans |
 Finn Voorhees
|
1bf681f90e
ggml : add error handling to graph_compute (whisper/1714)
|
il y a 2 ans |
|
Georgi Gerganov
|
c1d7cb28d3
ggml : do not sched_yield when calling BLAS (#4761)
|
il y a 2 ans |
|
Georgi Gerganov
|
3681f22443
examples : add few-shot translation example (#4783)
|
il y a 2 ans |
 Daniel Bevenius
|
b3a7c20b5c
finetune : remove unused includes (#4756)
|
il y a 2 ans |
|
Georgi Gerganov
|
012cf349ae
server : send token probs for "stream == false" (#4714)
|
il y a 2 ans |
|
Johannes Gäßler
|
a91928014f
Print backend name on test-backend-ops failure (#4751)
|
il y a 2 ans |
 singularity
|
3c0b585561
llama.swiftui : support loading custom model from file picker (#4767)
|
il y a 2 ans |
 Michael Coppola
|
e5804313a1
server : fix options in README.md (#4765)
|
il y a 2 ans |
|
Georgi Gerganov
|
dc891b7f7a
ggml : include stdlib.h before intrin.h (#4736)
|
il y a 2 ans |
|
singularity
|
46cea79e1f
llama.swiftui : fix build of ggml.metallib (#4754)
|
il y a 2 ans |
|
Daniel Bevenius
|
cb1e2818e0
train : fix typo in overlapping-samples help msg (#4758)
|
il y a 2 ans |
 Ashraful Islam
|
ece9a45e8f
swift : update Package.swift to use ggml as dependency (#4691)
|
il y a 2 ans |
|
Georgi Gerganov
|
7bed7eba35
cuda : simplify expression
|
il y a 2 ans |
|
Georgi Gerganov
|
d55356d3ba
cuda : mark I16 and I32 ops as unsupported
|
il y a 2 ans |
