issues
search
Mozilla-Ocho
/
llamafile
Distribute and run LLMs with a single file.
https://llamafile.ai
Other
16.71k
stars
827
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Support Flash Attention in server mode
#478
d-z-m
opened
1 day ago
0
Bug: stuck in extracting /zip/ggml-rocm.dll to /C/Users/x/.llamafile/v/0.8.7/ggml-rocm.dll
#476
xd2333
opened
3 days ago
1
update GGML_HIP_UMA
#473
Djip007
closed
1 week ago
0
llamafile vs llamacpp: the results model generate are different
#471
chong000
opened
2 weeks ago
2
Feature Request: New server UI from llama.cpp
#470
AmgadHasan
closed
2 weeks ago
1
Bug: Incompatible with Newest Qwen 2
#467
CJJ-amateur-programmer
opened
2 weeks ago
8
Bug: eos_token in LLM generated output
#465
tybalex
opened
3 weeks ago
2
Optimized matrix multiplications for i-quants on __aarch64__
#464
ikawrakow
closed
3 weeks ago
0
Run clang-format
#462
mrdomino
opened
3 weeks ago
0
Update sever README build/testing instructions
#461
veekaybee
closed
3 weeks ago
0
Upgrade to Cosmopolitan v3.3.10
#460
jeromew
closed
3 weeks ago
0
Hugging face repository does not show the version of the llamafile you are downloading
#459
norteo
opened
1 month ago
0
llama_sampling_init: failed to parse grammar
#458
cbail
closed
1 month ago
1
github: delete question in favor of link to discussion
#457
mofosyne
closed
1 month ago
1
github: add docker based ci github actions
#455
mofosyne
closed
1 month ago
1
github: add ci
#454
mofosyne
closed
1 month ago
2
Performance improvements on Arm for legacy and k-quants
#453
ikawrakow
closed
1 month ago
5
fix: update clip.h
#452
eltociear
closed
1 month ago
0
instruct chat templates
#451
CrispStrobe
opened
1 month ago
0
github: add mention of strace and ftrace
#449
mofosyne
closed
1 month ago
0
github: delete assignees and about --> description
#448
mofosyne
closed
1 month ago
0
get_amd_offload_arch_flag: warning: hipInfo output didn't list any graphics cards
#446
xd2333
closed
3 weeks ago
6
actions: auto close issue after 14 days
#444
mofosyne
closed
1 month ago
2
actions: add labeler + editorconfig github actions
#443
mofosyne
closed
1 month ago
0
github: add issue templates
#442
mofosyne
closed
1 month ago
0
AMD - tinyBLAS windows prebuilt support stopped working with 0.8.5
#441
jeromew
opened
1 month ago
23
Windows 10 GPU support bug
#440
jeaneric
opened
1 month ago
2
Added the ability to use LLAMA_HIP_UMA
#439
Djip007
closed
6 days ago
6
Is it possible for llamafile to use Vulkan or OpenCL Acceleration?
#438
Ff-c109
opened
1 month ago
9
Completion of error handling
#437
elfring
opened
1 month ago
0
Add Phi-3-mini-128k-instruct to README.md
#436
AlessandroW
closed
1 month ago
1
Another performance optimization for Zen4 + refactoring
#435
ikawrakow
closed
1 month ago
4
CUDA kernel vec_dot_q4_K_q8_1_impl_vmmq has no device code compatible with CUDA arch 600
#434
coder-vig
opened
1 month ago
1
unknown pre-tokenizer type: 'qwen2'
#432
sorasoras
opened
1 month ago
2
May I ask how to export and use LORA? I cannot use the BIN file converted with llama.cpp on my end
#431
cwyou123
opened
1 month ago
2
.llamafile folder corruption?
#429
Statixcinder
opened
1 month ago
0
Faster AVX2 matrix multiplications for MoE models
#428
ikawrakow
closed
1 month ago
4
Update llama.cpp for Meta-LLama-3
#427
Zibri
closed
1 month ago
1
A better gui?
#426
Zibri
opened
1 month ago
0
How to set context size? Running dolphin mixtral q4km, using too much of my 64gb of ram. want to lower it.
#425
FemBoxbrawl
closed
1 month ago
3
fail to load Qwen1.5-MoE-A2.7B-Chat on win10
#424
Rinoahu
opened
1 month ago
0
Update README.md
#423
isa10110
opened
1 month ago
0
add text embedding models to 'other example llamafiles' table
#422
k8si
closed
1 month ago
0
Build on Windows
#421
macbie
opened
1 month ago
2
How to run llamafile as a linux service
#420
fastdaima
closed
1 month ago
3
Add explanation for Windows user to how to Create EXE files
#419
fabiomatricardi
opened
1 month ago
4
Updated README with instructions to load models from third-party apps
#417
aittalam
closed
1 month ago
0
Can't run on AMD GPU, while llama.cpp does
#416
aasseman
opened
1 month ago
0
llamafile as LLM server for Mantella mod and Skyrim, is working nice but there is a little problem.
#415
amonpaike
opened
1 month ago
6
Are embeddings not supported with the mistral-7b-instruct-v0.2 model?
#414
norteo
closed
1 month ago
4
Next