Skip to content

update test #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 804 commits into from
Closed

update test #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
804 commits
Select commit Hold shift + click to select a range
6870c31
updated docs
LostRuins Nov 9, 2023
be92cfa
added preloadstory
LostRuins Nov 10, 2023
8849c11
remove unused func + fix entropy sampling again
kalomaze Nov 10, 2023
4a130ee
added support for filecomments
LostRuins Nov 10, 2023
cd57e17
remove experimental stuff
kalomaze Nov 10, 2023
a9005ab
oopsie
kalomaze Nov 10, 2023
df9d129
Unbreak persimmon after #3837 (#4010)
Galunid Nov 10, 2023
36e860e
updated docs
LostRuins Nov 10, 2023
a6e6b8b
Merge branch 'master' into concedo_experimental
LostRuins Nov 10, 2023
4b9a685
rename file comments to welcome
LostRuins Nov 10, 2023
4a4fd3e
server : allow continue edit on completion mode (#3950)
jhen0409 Nov 10, 2023
fd263bd
Update llama.cpp
kalomaze Nov 11, 2023
e08e1bd
include opencl dll
LostRuins Nov 11, 2023
027cd8c
Merge branch 'master' into concedo_experimental
LostRuins Nov 11, 2023
a00a32e
fixed localflag
LostRuins Nov 11, 2023
34b0a08
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3…
KerfuffleV2 Nov 11, 2023
d96ca7d
server : fix crash when prompt exceeds context size (#3996)
z80maniac Nov 11, 2023
e86fc56
Fix gguf-convert-endian script (#4037)
monatis Nov 11, 2023
532dd74
Fix some documentation typos/grammar mistakes (#4032)
richardkiss Nov 12, 2023
21fd874
gguf-py: gguf_writer: Use bytearray to build metadata (#4051)
KerfuffleV2 Nov 12, 2023
f4ee91a
improved estimation
LostRuins Nov 13, 2023
bb50a79
Add ReLU and SQR CUDA ops to (partially) fix Persimmon offloading (#4…
KerfuffleV2 Nov 13, 2023
4760e7c
sync : ggml (backend v2) (#3912)
ggerganov Nov 13, 2023
c049b37
readme : update hot topics
ggerganov Nov 13, 2023
3d68f36
ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060)
ggerganov Nov 13, 2023
bd90eca
llava : fix regression for square images in #3613 (#4056)
monatis Nov 13, 2023
b46d12f
convert.py: also look for plain model.safetensors (#4043)
afrideva Nov 14, 2023
36eed0c
stablelm : StableLM support (#3586)
Galunid Nov 14, 2023
6bb4908
Fix MacOS Sonoma model quantization (#4052)
TortoiseHam Nov 14, 2023
8b919b5
allow customized rope to use model set values
LostRuins Nov 15, 2023
35a97e1
Merge branch 'master' into concedo_experimental
LostRuins Nov 15, 2023
914e375
support custom dalle urls
LostRuins Nov 15, 2023
1cf2850
ggml-cuda : increase max graph size (#4084)
slaren Nov 15, 2023
a6fc554
llama : restore prefix space in llama tokenizer (#4081)
cebtenzzre Nov 15, 2023
a3f708a
added more fields to the openai compatible completions APIs
LostRuins Nov 15, 2023
8da4627
gguf : fix potential infinite loops while parsing (#4100)
texmex76 Nov 16, 2023
91f6499
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
KerfuffleV2 Nov 17, 2023
4f447a4
llama : fix data units (#4101)
ggerganov Nov 17, 2023
b83e149
cuda : get_row_rounding F32 (#4095)
AndrewGodfrey Nov 17, 2023
947f64f
finetune : zero the loraB initial vectors (#4082)
AndrewGodfrey Nov 17, 2023
3e916a0
finetune : speed-up ggml_compute_forward_out_prod_f32 via BLAS (#4079)
gwjr Nov 17, 2023
e85bb1a
llama : add functions to get the model's metadata (#4013)
slaren Nov 17, 2023
ba4cf5c
train : move number of gpu layers argument parsing to common/train.cp…
jpodivin Nov 17, 2023
f7d5e97
py : remove superfluous import statements (#4076)
jpodivin Nov 17, 2023
c7cce12
llava : fix compilation warning that fread return value is not used (…
huawei-lin Nov 17, 2023
9e87ef6
common : improve yaml log escaping (#4080)
joennlae Nov 17, 2023
11173c9
py : Falcon HF compatibility (#4104)
cmp-nct Nov 17, 2023
2ab0707
convert : use 'model' value if it exists. This allows karpathy/tinyll…
dmahurin Nov 17, 2023
2fa02b4
examples : add tokenize (#4039)
zakkor Nov 17, 2023
5ad387e
tokenize : fix trailing whitespace
ggerganov Nov 17, 2023
8e93610
build : support ppc64le build for make and CMake (#3963)
bufferoverflow Nov 17, 2023
bbecf3f
llama : increase max nodes (#4115)
slaren Nov 17, 2023
45ad1b9
max nodes 8192
LostRuins Nov 18, 2023
35ce2b0
typo fixes
LostRuins Nov 18, 2023
6bf8ee4
Merge branch 'master' into concedo_experimental
LostRuins Nov 18, 2023
22c56f9
default to multiuser
LostRuins Nov 18, 2023
2923f17
Clean up ggml-cuda.cu warnings when compiling with clang (for ROCM) (…
KerfuffleV2 Nov 18, 2023
0b5c3b0
scripts : Remove missed baichuan convert script (#4127)
Galunid Nov 18, 2023
28a2e6e
tokenize example: Respect normal add BOS token behavior (#4126)
KerfuffleV2 Nov 18, 2023
cf646fa
try to scale custom roped models
LostRuins Nov 19, 2023
e937066
gguf-py : export chat templates (#4125)
slaren Nov 19, 2023
35985ac
gitignore : tokenize
ggerganov Nov 19, 2023
262005a
common : comma should be semicolon (#4137)
kchro3 Nov 19, 2023
936c79b
server : relay error messages (#4131)
SoftwareRenderer Nov 19, 2023
05e8301
finetune : add --n-gpu-layers flag info to --help (#4128)
csaben Nov 19, 2023
dae06c0
Revert "finetune : add --n-gpu-layers flag info to --help (#4128)"
ggerganov Nov 19, 2023
40a34fe
speculative : fix prompt tokenization in speculative example (#4025)
AutonomicPerfectionist Nov 20, 2023
f23c035
ci : add flake8 to github actions (python linting) (#4129)
Galunid Nov 20, 2023
881800d
main : Add ChatML functionality to main example (#4046)
Sebby37 Nov 20, 2023
dc4078c
fixed segfault with all non-gguf models
LostRuins Nov 20, 2023
4d7c14b
fix stop seq escaping newline
LostRuins Nov 20, 2023
56a5fa7
Merge branch 'master' into concedo_experimental
LostRuins Nov 20, 2023
dfc7cd4
readme : update ROCm Windows instructions (#4122)
jammm Nov 20, 2023
0b871f1
finetune - update readme to mention llama support only (#4148)
Galunid Nov 20, 2023
1f57eb8
Merge branch 'LostRuins:concedo' into exp-dynatemp-minp-latest
kalomaze Nov 20, 2023
bab8b19
unused binary search + double softmax precision
kalomaze Nov 20, 2023
18fae61
Merge branch 'exp-dynatemp-minp-latest' of https://github.com/kalomaz…
kalomaze Nov 20, 2023
8e672ef
stablelm : simplify + speedup generation (#4153)
Galunid Nov 21, 2023
ff8238f
docs : add llama-star arch idea
ggerganov Nov 23, 2023
9d5949f
examples : fix typo in parallel example doc comment (#4181)
danbev Nov 23, 2023
d103d93
readme : update hot topics
ggerganov Nov 23, 2023
6b0a742
llama : KV cache view API + better KV cache management (#4170)
ggerganov Nov 23, 2023
55978ce
Fix incorrect format strings and uninitialized variables. (#4133)
haohui Nov 23, 2023
eb42c73
revert auto rope scaling for already-ropetuned models - just use thei…
LostRuins Nov 24, 2023
b35f3d0
readme : use PATH for Windows ROCm (#4195)
jammm Nov 24, 2023
2568a4b
main.swift : fix eos checking (#4197)
eastriverlee Nov 24, 2023
189d684
convert : fix tensors using grad in some models (#4173)
Galunid Nov 24, 2023
8a052c1
ggml-cuda : support stablelm rope (#4156)
slaren Nov 24, 2023
e9c13ff
llama : set metal log callback correctly (#4204)
slaren Nov 24, 2023
af19d35
server : OAI API compatibility (#4198)
ggerganov Nov 25, 2023
04814e7
readme : update hot topics
ggerganov Nov 25, 2023
3014b54
Update docs for yarn_ext_factor <0.0 as unspecified instead of NaN (#…
crasm Nov 25, 2023
f837c3a
llama : grammar `reserve` space in `decode_utf8` (#4210)
MarcusDunn Nov 25, 2023
1ddb52e
scripts : Use mmap in torch load (#4202)
Galunid Nov 25, 2023
22da055
metal : fix yarn (#4220)
jxy Nov 26, 2023
a6eb9b8
Fix GPT2 not loading due to graph too small
LostRuins Nov 26, 2023
bffa781
explore quiet mode
LostRuins Nov 26, 2023
2f51a6a
trigger quiet mode when selecting remotetunnel
LostRuins Nov 26, 2023
922754a
lookahead : add example for lookahead decoding (#4207)
ggerganov Nov 26, 2023
9656026
readme : update hot topics
ggerganov Nov 26, 2023
3e73d31
lookahead : support `-n -1` infinite generation
ggerganov Nov 26, 2023
f3b2698
ggml : fix -Warray-bounds warning with gcc (#4231)
cebtenzzre Nov 27, 2023
ec1796b
updated lite
LostRuins Nov 27, 2023
8acd7be
Merge branch 'master' into concedo_experimental
LostRuins Nov 27, 2023
0e5f16d
reduce max ctx to fit instead of crashing
LostRuins Nov 27, 2023
bb03290
examples : iOS example with swift ui (#4159)
bachittle Nov 27, 2023
0dab8cd
readme : add Amica to UI list (#4230)
kasumi-1 Nov 27, 2023
b38a16d
cmake : fix issue with version info not getting baked into LlamaConfi…
bandoti Nov 27, 2023
b556da2
Noisy sampling experiment
kalomaze Nov 27, 2023
8406b09
ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant ful…
ggerganov Nov 28, 2023
d2ef458
show more info about available APIs
LostRuins Nov 28, 2023
64e64aa
ggml : restore abort() in GGML_ASSERT (#4242)
cebtenzzre Nov 28, 2023
ba5c333
Allocate a small amount of extra context for GGUF to deal with KV fra…
LostRuins Nov 28, 2023
581021a
Merge branch 'master' into concedo_experimental
LostRuins Nov 28, 2023
b75152e
added a proper quiet mode
LostRuins Nov 28, 2023
66ef4a2
refined multiuser mode
LostRuins Nov 29, 2023
4fea342
readme : add FreeChat (#4248)
psugihara Nov 29, 2023
1f5cd83
examples : add readme files
ggerganov Nov 29, 2023
a012342
updated docs, shifted kv extra space to be subtracted from user's ctx…
LostRuins Nov 30, 2023
e9724cd
Merge branch 'master' into concedo_experimental
LostRuins Nov 30, 2023
a195cde
fixed chub ai imports (+1 squashed commits)
LostRuins Nov 30, 2023
e2bd725
py : fix oai proxy (#3972)
rhjdvsgsgks Nov 30, 2023
954e228
llama : fix typical sampling (#4261)
tarcey Nov 30, 2023
f4d973c
convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#4258)
slaren Nov 30, 2023
b18c66c
llama : fix alignment of general.name in print meta (#4254)
danbev Nov 30, 2023
74daaba
readme : fix typo (#4253)
TortillaZHawaii Nov 30, 2023
f7f9e06
cmake : fix the metal file foder path (#4217)
tanliboy Nov 30, 2023
bde629b
batched.swift : update README.md (#4214)
ensan-hcl Nov 30, 2023
3bd2c7c
docker : add finetune option (#4211)
jooray Nov 30, 2023
524907a
readme : fix (#4135)
vodkaslime Nov 30, 2023
8efa0f6
main : pass LOG_TEE callback to llama.cpp log (#4033)
AndrewGodfrey Nov 30, 2023
33c9892
llava : ShareGPT4V compatibility (vision encoder only loading) (#4172)
cmp-nct Nov 30, 2023
15f5d96
build : fix build info generation and cleanup Makefile (#3920)
cebtenzzre Nov 30, 2023
d2809a3
make : fix Apple clang determination bug (#4272)
Nov 30, 2023
f43f093
server : add single-client multi-prompt support (#4232)
ziedbha Nov 30, 2023
1d14411
server : add --log-disable to disable logging to file (#4260)
ziedbha Nov 30, 2023
ef47ec1
ggml : add ggml_soft_max_ext (#4256)
ggerganov Dec 1, 2023
8d6d9f0
py : add requirements file for convert-hf-to-gguf.py (#4277)
danbev Dec 1, 2023
4f40c22
Merge branch 'master' into concedo_experimental
LostRuins Dec 1, 2023
495bb3a
Merge branch 'master' into concedo_experimental
LostRuins Dec 1, 2023
880f579
llama : fix integer overflow during quantization (#4284)
ggerganov Dec 1, 2023
37c746d
llama : add Qwen support (#4281)
simonJJJ Dec 1, 2023
03562f3
llama : support attention bias on LLaMA architecture (#4283)
RealJosephus Dec 1, 2023
511f52c
build : enable libstdc++ assertions for debug builds (#4275)
cebtenzzre Dec 1, 2023
b220222
swift : fix token_to_piece implementation (#4278)
ensan-hcl Dec 1, 2023
d5a1cbd
llama : support optional tensors (#4283)
ggerganov Dec 1, 2023
5a7d312
llama : avoid using "optional" keyword (#4283)
ggerganov Dec 1, 2023
1c422f4
more printouts
LostRuins Dec 2, 2023
12f66ea
adjust fragmentation fix
LostRuins Dec 2, 2023
a829a1e
fix for janitorai
LostRuins Dec 2, 2023
a8e66ef
Revert "ggml : add ggml_soft_max_ext (#4256)"
LostRuins Dec 2, 2023
c142c56
fixed segfault with clblast by reversing commit in issue https://gith…
LostRuins Dec 2, 2023
0ca814e
added minP preset
LostRuins Dec 3, 2023
6570a20
token count includes ids
LostRuins Dec 3, 2023
d7b800b
llama : pad KV cache size (#4280)
ggerganov Dec 3, 2023
6949b50
py : add grammar to oai like api (#4294)
neph1 Dec 3, 2023
33e171d
server : fix OpenAI API `stop` field to be optional (#4299)
Mardak Dec 3, 2023
48544cd
Revert "Revert "ggml : add ggml_soft_max_ext (#4256)""
LostRuins Dec 3, 2023
adf3de4
ggml : fix soft max out-of-bounds access (#4307)
ggerganov Dec 3, 2023
ac36aee
Merge branch 'master' into concedo_experimental
LostRuins Dec 3, 2023
fbbc428
ggml : reuse ggml_get_n_tasks() in ggml_graph_plan() (#4308)
ggerganov Dec 3, 2023
8602f5a
Merge branch 'master' into concedo_experimental
LostRuins Dec 3, 2023
4fa44e8
grammar-parser : fix typo (#4318)
eltociear Dec 4, 2023
a5a5839
handle accidentally selecting a kcpps file as model instead
LostRuins Dec 4, 2023
5c9f90c
swift : fix prompt tokenization logic (#4321)
ensan-hcl Dec 4, 2023
d208995
swift : fix concatenation method to avoid invalid UTF8 stringfication…
ensan-hcl Dec 4, 2023
23b5e12
simple : update error message for KV cache check (#4324)
danbev Dec 4, 2023
e4b76bb
swift : revert compiler checks for swift package (#4332)
kchro3 Dec 5, 2023
52c8bc3
sampling : custom samplers order (#4285)
MaggotHATE Dec 5, 2023
b6f952f
improved exit logic
LostRuins Dec 5, 2023
5aa365d
llama : allow overriding GGUF metadata when loading model (#4092)
KerfuffleV2 Dec 5, 2023
5f6e0c0
grammar : pre-computed pieces + reserve mem + less string copies (#4330)
MarcusDunn Dec 5, 2023
da5eaef
speculative : support `--color` (#4343)
stduhpf Dec 6, 2023
caa9249
common : fix compile warning
ggerganov Dec 6, 2023
12002d8
very basic noscript mode
LostRuins Dec 6, 2023
c751152
noscript mode is done
LostRuins Dec 6, 2023
05cd6e5
server : recognize cache_prompt parameter in OAI API (#4347)
ggerganov Dec 6, 2023
81bc921
train : fix #4227 (double free in examples/train-text-from-scratch/tr…
casavaca Dec 7, 2023
bcc0eb4
llama : per-layer KV cache + quantum K cache (#4309)
ggerganov Dec 7, 2023
fe680e3
sync : ggml (new ops, tests, backend, etc.) (#4359)
ggerganov Dec 7, 2023
930cdfb
updated lite, added patch that links to noscript mode
LostRuins Dec 8, 2023
ec21fa7
Merge branch 'master' into concedo_experimental
LostRuins Dec 8, 2023
7469f20
use lowvram flag for offload qkv
LostRuins Dec 8, 2023
c47bc28
slight refactor for noscript ui
LostRuins Dec 8, 2023
7418bca
up ver
LostRuins Dec 8, 2023
7a69152
lowvram var defaults
LostRuins Dec 8, 2023
e18f734
grammar : revert the replacement of llama_token_to_piece with id_to_t…
AlienKevin Dec 9, 2023
e2cf3b7
koboldcpp.sh - The Mamba Multitool (#554)
henk717 Dec 10, 2023
8a7b2fa
Update README.md (#4388)
y10ab1 Dec 10, 2023
4b854d4
Hide hipBLAS (ROCm) if CuBLAS exists - vice versa
YellowRoseCx Dec 11, 2023
fce971d
do not build the clblast noavx2 binary if not on windows
LostRuins Dec 11, 2023
06581f2
perf endpoint lets you monitor if the embedded horde worker has issues
LostRuins Dec 11, 2023
74acc54
Revert "Hide hipBLAS (ROCm) if CuBLAS exists - vice versa"
LostRuins Dec 12, 2023
0d4a198
Merge branch 'LostRuins:concedo' into exp-dynatemp-minp-latest
kalomaze Dec 12, 2023
edf3ff7
Turn off noisy sampling by default
kalomaze Dec 12, 2023
41a11aa
ggml : increased GGML_MAX_PARAMS to allow finetuning of 70b models (#…
Taikono-Himazin Dec 12, 2023
d9d4cfe
server : fix local model name in server (#4420)
epicfilemcnulty Dec 12, 2023
6391817
llama : document logits_all deprecation (#4418)
crasm Dec 12, 2023
6138963
build : target Windows 8 for standard mingw-w64 (#4405)
cebtenzzre Dec 12, 2023
9494d7c
english : use `typos` to fix comments and logs (#4354)
richardkiss Dec 12, 2023
fecac45
server : tweak default sampling parameters (#4367)
kalomaze Dec 12, 2023
4db9586
do not display the "maybe" MMQ console output
LostRuins Dec 13, 2023
c2c238b
Merge branch 'master' into concedo_experimental
LostRuins Dec 13, 2023
799a1cb
llama : add Mixtral support (#4406)
slaren Dec 13, 2023
113f994
readme : update hot topics
ggerganov Dec 13, 2023
9fb13f9
common : add `--version` option to show build info in CLI (#4433)
yusiwen Dec 13, 2023
e447af6
Merge branch 'master' into concedo_experimental
LostRuins Dec 13, 2023
2810151
update docs
LostRuins Dec 13, 2023
3067547
Koboldcpp.sh Fix & Nocuda (#562)
henk717 Dec 13, 2023
70f806b
build : detect host compiler and cuda compiler separately (#4414)
cebtenzzre Dec 13, 2023
4d98d9a
sync : ggml (SD ops, tests, kernels) (#4444)
ggerganov Dec 13, 2023
948ff13
server : fix handling of characters that span multiple tokens when st…
shibe2 Dec 13, 2023
ec2cf6c
Merge branch 'concedo' into concedo_experimental
LostRuins Dec 14, 2023
8dd9756
removing existing yml files
LostRuins Dec 14, 2023
146e3bb
Automatically generate Linux Binaries (#564)
henk717 Dec 14, 2023
0e31f53
Revert "lowvram var defaults"
LostRuins Dec 14, 2023
0353a18
readme : update supported model list (#4457)
BarfingLemurs Dec 14, 2023
1ad8f0d
Fixes "Not enough space in the context's memory pool" encountered on …
LostRuins Dec 14, 2023
873637a
convert : support loading vocab from fast tokenizer config (#3633)
strutive07 Dec 14, 2023
34b3dac
Fixes "Not enough space in the context's memory pool" encountered on …
LostRuins Dec 14, 2023
c88fc19
Merge branch 'master' into concedo_experimental
LostRuins Dec 14, 2023
55e87c3
ggml : fix OpenCL broadcast requirement for ggml_mul (close #4453)
ggerganov Dec 14, 2023
05f7db4
do not cast to size_t, instead just use doubles
LostRuins Dec 14, 2023
53bbd1e
Merge branch 'pr_fix_buf_resize_type' into concedo_experimental
LostRuins Dec 14, 2023
04bd895
Revert "Fixes "Not enough space in the context's memory pool" encount…
LostRuins Dec 14, 2023
f0de495
fixed length exceeding max ctx
LostRuins Dec 14, 2023
aac7f0b
Merge branch 'master' into concedo_experimental
LostRuins Dec 14, 2023
ae3d829
manual workflow for generating builds instead
LostRuins Dec 14, 2023
7798587
Workflow Build from experimental branch
LostRuins Dec 14, 2023
20a68a7
ggml : add ggml_row_size() (fixes llama out of space) (#4461)
LostRuins Dec 14, 2023
c50e400
py : add protobuf dependency (#4466)
strutive07 Dec 14, 2023
cafcd4f
ggml : remove n_dims from ggml_tensor (#4469)
slaren Dec 14, 2023
6744dbe
ggml : use ggml_row_size where possible (#4472)
slaren Dec 14, 2023
ee4725a
ggml : group mul_mat_id rows by matrix (cpu only) (#4480)
slaren Dec 15, 2023
88ae895
server : add optional API Key Authentication example (#4441)
ShadovvBeast Dec 15, 2023
21c1421
Merge pull request #4 from kalomaze/concedo
kalomaze Dec 15, 2023
062f668
Change override values for DynaTemp variants
kalomaze Dec 15, 2023
8a5be3b
llama : sanity checks for access to logits (#4274)
cebtenzzre Dec 16, 2023
76a3ba4
Merge branch 'master' into concedo_experimental
LostRuins Dec 16, 2023
c6c4fc0
lora : add support for non-llama models (#3333)
slaren Dec 16, 2023
774f2cb
Add experimental custom routing for MoE
kalomaze Dec 13, 2023
1ea28d6
Change default expert count to 2
kalomaze Dec 13, 2023
e8cf7f6
Merge remote-tracking branch 'origin/master' into concedo_experimental
LostRuins Dec 17, 2023
ec05230
updated lite, up ver
LostRuins Dec 17, 2023
4c975c0
Add temp_sim script + tweak dynatemp entropy
kalomaze Dec 17, 2023
6009778
Revert "Change default expert count to 2"
kalomaze Dec 17, 2023
4fd1b2f
Revert "Add experimental custom routing for MoE"
kalomaze Dec 17, 2023
de9e0f3
Update DynaTemp branch with mainline improvements
kalomaze Dec 17, 2023
97fa427
CUDA: Faster Mixtral prompt processing (#4538)
JohannesGaessler Dec 20, 2023
92497e1
CUDA: mul_mat_id always on GPU for batches >= 32
JohannesGaessler Dec 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 0 additions & 33 deletions .devops/full-cuda.Dockerfile
View file
Open in desktop

This file was deleted.

44 changes: 0 additions & 44 deletions .devops/full-rocm.Dockerfile
View file
Open in desktop

This file was deleted.

84 changes: 0 additions & 84 deletions .devops/llama-cpp-clblast.srpm.spec
View file
Open in desktop

This file was deleted.

83 changes: 0 additions & 83 deletions .devops/llama-cpp-cublas.srpm.spec
View file
Open in desktop

This file was deleted.

85 changes: 0 additions & 85 deletions .devops/llama-cpp.srpm.spec
View file
Open in desktop

This file was deleted.

32 changes: 0 additions & 32 deletions .devops/main-cuda.Dockerfile
View file
Open in desktop

This file was deleted.

Loading