issues
search
exo-explore
/
exo
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
GNU General Public License v3.0
6.56k
stars
342
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[BOUNTY - $500] Llama.cpp inference engine
#167
AlexCheema
opened
3 weeks ago
6
simplify formatting with yapf
#166
AlexCheema
closed
3 weeks ago
0
Enhancement: support local and custom models
#165
vlbosch
opened
3 weeks ago
0
BUG: Spaces between words are not streamed
#164
vlbosch
closed
3 weeks ago
11
python issues
#163
zaidzameeer010
opened
3 weeks ago
1
Running on 32bit PowerPC
#162
nonetrix
opened
3 weeks ago
0
add support for running exo in cli with --run-model <model> --prompt <prompt>
#161
AlexCheema
closed
3 weeks ago
0
Error processing tensor for shard when loading model on Android devices
#160
artistlu
opened
3 weeks ago
0
[BOUNTY - $500] Distributed stable diffusion
#159
AlexCheema
opened
3 weeks ago
6
About #130, regarding subsequential requests
#158
psj900918-r5
closed
3 weeks ago
1
Astra
#157
AlexCheema
closed
3 weeks ago
1
Unstable node connection and model loading error when using Termux with Proot on multiple Android devices
#156
artistlu
closed
3 weeks ago
2
Having trouble running on ubuntu linux with 4090 (cuda 12.2)
#155
ctisme
opened
4 weeks ago
5
Load local autoprocessor rather than always get autoprocessor from huggingface.
#154
JosiahWayne
opened
1 month ago
0
A request
#153
tml2024
opened
1 month ago
0
Android device loading model reports CLANG error
#152
fangxuezheng
opened
1 month ago
2
Add common RTX A series cards to device_capabilities.py
#151
sammcj
closed
1 month ago
1
flow-based partitioning strategy
#150
AlexCheema
opened
1 month ago
0
automatically determine estimate of device FLOPs
#149
AlexCheema
opened
1 month ago
0
[BOUNTY - $300] Add support for quantized models with tinygrad
#148
AlexCheema
opened
1 month ago
3
cannot run in WSLs with CPUs only.
#147
mct2611
opened
1 month ago
5
local model loading without request to huggingface
#146
artistlu
opened
1 month ago
2
Mali GPU OpenCL does not support bfloat16
#145
artistlu
opened
1 month ago
2
在进行推理时会一直不停止的输出
#144
JKYtydt
closed
1 month ago
1
"failed to connect to all addresses; last error: UNAVAILABLE: ipv4:127.0.0.1:7897: Socket closed"
#143
lesong36
opened
1 month ago
2
SyntaxError: f-string expression part cannot include a backslash
#142
PLK2
closed
1 month ago
2
Multiple nodes do not speed up inference on large models
#141
wzLLM
opened
1 month ago
2
Issues loading model shards
#140
barsuna
opened
1 month ago
4
[Bounty] PyTorch & HuggingFace Interface
#139
risingsunomi
opened
1 month ago
4
add --max-parallel-downloads flag that limits the number of downloads fixes #137, use async for all file ops, cache fetch_file_list, cache commit hash, quickly check file sizes on disk before making requests
#138
AlexCheema
closed
1 month ago
0
Enhancement: Allow to download shards in series within 1 device
#137
barsuna
closed
1 month ago
3
add --download-quick-check flag to bypass the hf api calls / remote f…
#136
AlexCheema
closed
1 month ago
0
display all interfaces web chat and chatgpt api are available on fixe…
#135
AlexCheema
closed
1 month ago
0
Display all interfaces that exo is started on
#134
AlexCheema
closed
1 month ago
0
使用exo+mlx多台mac运行llama-3.1-70b,返现量化时报错[BUG]
#133
wjwc
opened
1 month ago
3
[EXPLORATION] comfyui
#132
AlexCheema
opened
1 month ago
2
Docs: Linux Example Script
#131
da-moon
opened
1 month ago
1
Error processing tensor for shard Shard(model_id='mlx-community/Meta-Llama-3.1-8B-Instruct-4bit', start_layer=16, end_layer=31, n_layers=32): Shapes (1,8,4,39,77) and (39,39) cannot be broadcast
#130
wzLLM
closed
1 month ago
5
Max tokens limits responses on a given request_id
#129
AlexCheema
opened
1 month ago
0
OOM error when loading model using load_state_dict on multiple Mali GPU devices
#128
artistlu
closed
1 month ago
0
feat: Add p2p download functionality
#127
gauravsaini
opened
1 month ago
1
feat: Add file broadcasting and downloading functionality
#126
gauravsaini
closed
1 month ago
0
feat(docker): add dockerfile to build
#125
dan-online
closed
1 month ago
3
Refactor model download
#124
AlexCheema
closed
1 month ago
1
Multi-GPU on same device
#123
AlexCheema
opened
1 month ago
1
Only detects 1/2 Nvidia GPUs, doesn't find macbook over the same local network.
#122
reasv
opened
1 month ago
3
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xf8 in position 0: invalid start byte
#121
reasv
closed
1 month ago
2
await self.inference_engine.infer_tensor(request_id, shard, tensor, inference_state=inference_state)
#120
kawayuta
opened
1 month ago
2
Add support for Linux distributions and Docker containers
#119
rekpero
opened
1 month ago
0
Can I set the maximum exo memory usage for each node? Prevent oom
#118
artistlu
opened
1 month ago
1
Previous
Next