Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / exo-explore/exo issues and pull requests
#184 - Error on Windows 11: "NotImplementedError" in asyncio
Issue -
State: open - Opened by TheFilipcom4607 3 months ago
- 7 comments
#183 - Add Llama.cpp Support
Pull Request -
State: closed - Opened by bayedieng 3 months ago
- 10 comments
#173 - Docker Image
Pull Request -
State: open - Opened by Scot-Survivor 3 months ago
- 21 comments
#170 - Tailscale Discovery Module
Issue -
State: closed - Opened by AlexCheema 3 months ago
- 1 comment
#168 - Thunderbolt Connection Causes LLM Requests to Freeze When One Mac Is Offline and the Other Is Connected to a Network
Issue -
State: open - Opened by mcollins123 3 months ago
- 2 comments
#167 - [BOUNTY - $500] Llama.cpp inference engine
Issue -
State: open - Opened by AlexCheema 3 months ago
- 9 comments
#155 - Having trouble running on ubuntu linux with 4090 (cuda 12.2)
Issue -
State: open - Opened by ctisme 3 months ago
- 6 comments
#153 - A request
Issue -
State: closed - Opened by tml2024 3 months ago
- 2 comments
Labels: enhancement, good first issue
#146 - local model loading without request to huggingface
Issue -
State: open - Opened by artistlu 3 months ago
- 3 comments
Labels: enhancement
#139 - [Bounty] PyTorch & HuggingFace Interface
Pull Request -
State: open - Opened by risingsunomi 3 months ago
- 88 comments
#133 - 使用exo+mlx多台mac运行llama-3.1-70b,返现量化时报错[BUG]
Issue -
State: open - Opened by wjwc 3 months ago
- 4 comments
Labels: help wanted
#111 - Compatibility with Raspberry Pi
Issue -
State: open - Opened by bowenjw 3 months ago
- 3 comments
#109 - A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.0
Issue -
State: open - Opened by bricolage 3 months ago
- 3 comments
#101 - CUDA Error 2, out of memory
Issue -
State: open - Opened by fangxuezheng 3 months ago
- 11 comments
#100 - How install on android
Issue -
State: open - Opened by artistlu 3 months ago
- 7 comments
#100 - How install on android
Issue -
State: open - Opened by artistlu 3 months ago
- 7 comments
#99 - Bittorrent to distribute models amongst nodes
Issue -
State: open - Opened by austinbv 3 months ago
- 5 comments
Labels: enhancement, help wanted
#99 - Bittorrent to distribute models amongst nodes
Issue -
State: open - Opened by austinbv 3 months ago
- 5 comments
Labels: enhancement, help wanted
#98 - Does not recognize tokenizer.json
Issue -
State: open - Opened by hafezmg48 3 months ago
#97 - Can a large model be successfully loaded across multiple EXO nodes with insufficient individual memory?
Issue -
State: open - Opened by artistlu 3 months ago
- 6 comments
#97 - Can a large model be successfully loaded across multiple EXO nodes with insufficient individual memory?
Issue -
State: open - Opened by artistlu 3 months ago
- 6 comments
#96 - 从本地加载模型
Issue -
State: open - Opened by JKYtydt 4 months ago
- 4 comments
#95 - Error loading local model on Mali GPU
Issue -
State: open - Opened by artistlu 4 months ago
- 1 comment
#95 - Error loading local model on Mali GPU
Issue -
State: open - Opened by artistlu 4 months ago
- 1 comment
#94 - refactor(mlx): model sharding and add deepseek v2 support
Pull Request -
State: closed - Opened by mzbac 4 months ago
- 1 comment
#94 - refactor(mlx): model sharding and add deepseek v2 support
Pull Request -
State: closed - Opened by mzbac 4 months ago
- 1 comment
#93 - Generate swift inference engine using tinygrad
Issue -
State: open - Opened by AlexCheema 4 months ago
#93 - Generate swift inference engine using tinygrad
Issue -
State: open - Opened by AlexCheema 4 months ago
#92 - Keep waiting for response after initiating a chat request
Issue -
State: closed - Opened by duguyixiaono1 4 months ago
- 1 comment
#92 - Keep waiting for response after initiating a chat request
Issue -
State: closed - Opened by duguyixiaono1 4 months ago
- 1 comment
#91 - mistral large 2 support
Issue -
State: closed - Opened by win4r 4 months ago
- 1 comment
#91 - mistral large 2 support
Issue -
State: closed - Opened by win4r 4 months ago
- 1 comment
#90 - Ignore binary messages from MikroTik routers
Pull Request -
State: closed - Opened by xeb 4 months ago
- 4 comments
#89 - Running only in CPU
Issue -
State: closed - Opened by ManuXD32 4 months ago
- 3 comments
#88 - Support for LLaVA
Pull Request -
State: closed - Opened by varshith15 4 months ago
- 11 comments
#88 - Support for LLaVA
Pull Request -
State: closed - Opened by varshith15 4 months ago
- 11 comments
#87 - refactor(mlx): model sharding and add deepseek v2 support
Pull Request -
State: closed - Opened by mzbac 4 months ago
- 4 comments
#87 - refactor(mlx): model sharding and add deepseek v2 support
Pull Request -
State: closed - Opened by mzbac 4 months ago
- 4 comments
#86 - Correct llama 3.1 405b huggingface ID
Pull Request -
State: closed - Opened by sammcj 4 months ago
- 2 comments
#86 - Correct llama 3.1 405b huggingface ID
Pull Request -
State: closed - Opened by sammcj 4 months ago
- 2 comments
#85 - AttributeError: 'GRPCPeerHandle' object has no attribute 'global_reset'
Issue -
State: closed - Opened by alphrc 4 months ago
- 2 comments
#84 - Refactor mlx model sharding
Issue -
State: open - Opened by mzbac 4 months ago
- 4 comments
#83 - module load failed with status code 222: CUDA_ERROR_UNSUPPORTED_PTX_VERSION
Issue -
State: open - Opened by fangxuezheng 4 months ago
- 2 comments
#83 - module load failed with status code 222: CUDA_ERROR_UNSUPPORTED_PTX_VERSION
Issue -
State: open - Opened by fangxuezheng 4 months ago
- 2 comments
#82 - Can Exo run smaller language models on my Mali GPU device with 3GB RAM?
Issue -
State: open - Opened by artistlu 4 months ago
- 1 comment
#82 - Can Exo run smaller language models on my Mali GPU device with 3GB RAM?
Issue -
State: open - Opened by artistlu 4 months ago
- 1 comment
#81 - Message.init() got an unexpected keyword argument 'name' + FIX
Issue -
State: closed - Opened by stephanj 4 months ago
- 1 comment
#80 - Can I manually download model files if my server cannot access huggingface.co?
Issue -
State: open - Opened by artistlu 4 months ago
- 3 comments
#80 - Can I manually download model files if my server cannot access huggingface.co?
Issue -
State: open - Opened by artistlu 4 months ago
- 3 comments
#79 - Allow LLM copy from the local network instead of downloading from Hugging Face
Issue -
State: open - Opened by stephanj 4 months ago
- 4 comments
#78 - Regarding the issue of mlx_lm. tokenizer_utils
Issue -
State: open - Opened by fangxuezheng 4 months ago
- 6 comments
#77 - Update device_capabilities.py (first PR ever... hope I did okay lol)
Pull Request -
State: closed - Opened by Cloud1590 4 months ago
- 4 comments
#76 - NVML Shared Library Not Found on ARM64 platform with Mali GPU
Issue -
State: closed - Opened by artistlu 4 months ago
- 2 comments
#76 - NVML Shared Library Not Found on ARM64 platform with Mali GPU
Issue -
State: closed - Opened by artistlu 4 months ago
- 2 comments
#75 - Router Packets not decodable
Issue -
State: closed - Opened by xeb 4 months ago
- 4 comments
#75 - Router Packets not decodable
Issue -
State: closed - Opened by xeb 4 months ago
- 4 comments
#74 - Fix #73 - Calcs now correctly the TFLOPS for MacBook Pro M1 Max
Pull Request -
State: open - Opened by stephanj 4 months ago
- 7 comments
#74 - Fix #73 - Calcs now correctly the TFLOPS for MacBook Pro M1 Max
Pull Request -
State: open - Opened by stephanj 4 months ago
- 7 comments
#73 - Showing 0 TFLOPS for MacBook Pro node
Issue -
State: open - Opened by stephanj 4 months ago
- 1 comment
#73 - Showing 0 TFLOPS for MacBook Pro node
Issue -
State: open - Opened by stephanj 4 months ago
- 1 comment
#72 - Windows progress
Issue -
State: open - Opened by small-cactus 4 months ago
- 1 comment
#72 - Windows progress
Issue -
State: open - Opened by small-cactus 4 months ago
- 1 comment
#71 - Incorrect statitics
Issue -
State: open - Opened by magnusviri 4 months ago
#71 - Incorrect statitics
Issue -
State: open - Opened by magnusviri 4 months ago
#70 - Model only downloads 1 node at a time.
Issue -
State: closed - Opened by magnusviri 4 months ago
- 4 comments
#70 - Model only downloads 1 node at a time.
Issue -
State: closed - Opened by magnusviri 4 months ago
- 4 comments
#69 - Cannot create a proper connection between two Macs
Issue -
State: open - Opened by ponnhide 4 months ago
- 8 comments
#68 - Advantage over Groq
Issue -
State: closed - Opened by INF800 4 months ago
- 1 comment
#67 - cache per request
Issue -
State: closed - Opened by AlexCheema 4 months ago
- 2 comments
#66 - Llama-3-405b
Issue -
State: closed - Opened by AlexCheema 4 months ago
- 1 comment
#66 - Llama-3-405b
Issue -
State: closed - Opened by AlexCheema 4 months ago
- 1 comment
#65 - Still need to access the web server hosted by the tail node ?
Issue -
State: closed - Opened by southkorea2013 4 months ago
- 1 comment
#64 - Enhancement Request
Issue -
State: open - Opened by southkorea2013 4 months ago
#64 - Enhancement Request
Issue -
State: open - Opened by southkorea2013 4 months ago
#63 - Suggestion: create a section that list projects using Exo!
Issue -
State: open - Opened by nicarq 4 months ago
- 1 comment
#63 - Suggestion: create a section that list projects using Exo!
Issue -
State: open - Opened by nicarq 4 months ago
- 1 comment
#62 - Adding a node while it's doing inference messes it up.
Issue -
State: open - Opened by magnusviri 4 months ago
#62 - Adding a node while it's doing inference messes it up.
Issue -
State: open - Opened by magnusviri 4 months ago
#61 - No way to cancel
Issue -
State: open - Opened by magnusviri 4 months ago
- 4 comments
#60 - No feedback and very long delay
Issue -
State: closed - Opened by magnusviri 4 months ago
- 5 comments
#59 - how to increase max tokens in tinychat?
Issue -
State: closed - Opened by arthur-brainchain 4 months ago
- 1 comment
#58 - Inference engine selection improvements
Pull Request -
State: closed - Opened by jakobdylanc 4 months ago
- 1 comment
#58 - Inference engine selection improvements
Pull Request -
State: closed - Opened by jakobdylanc 4 months ago
- 1 comment
#57 - Response generation timed out
Issue -
State: open - Opened by caohuilong 4 months ago
- 2 comments
#57 - Response generation timed out
Issue -
State: open - Opened by caohuilong 4 months ago
- 2 comments
#56 - 15 nodes, job not divided properly
Issue -
State: open - Opened by magnusviri 4 months ago
- 4 comments
#56 - 15 nodes, job not divided properly
Issue -
State: open - Opened by magnusviri 4 months ago
- 4 comments
#55 - Will the tokens/s be increasing after adding more nodes to the cluster?
Issue -
State: open - Opened by southkorea2013 4 months ago
- 3 comments
#55 - Will the tokens/s be increasing after adding more nodes to the cluster?
Issue -
State: open - Opened by southkorea2013 4 months ago
- 3 comments
#54 - How to set the max tokens for web ui?
Issue -
State: closed - Opened by southkorea2013 4 months ago
- 4 comments
#53 - Consider allowing IPv4 exposure for a working node
Issue -
State: closed - Opened by Hax0rG1rl 4 months ago
- 4 comments
#52 - [BOUNTY - $200] Share kv cache between nodes for redundancy
Issue -
State: open - Opened by AlexCheema 4 months ago
- 12 comments
Labels: enhancement
#51 - Switch grpc peer connections over to the best interface available
Issue -
State: open - Opened by AlexCheema 4 months ago
#50 - Add our own runners for CI/CD
Issue -
State: open - Opened by AlexCheema 4 months ago
#49 - Flag to disable Viz TUI
Pull Request -
State: closed - Opened by apotl 4 months ago
- 1 comment
#48 - Implement dynamic inference engine selection #45
Pull Request -
State: closed - Opened by itsknk 4 months ago
- 7 comments
#48 - Implement dynamic inference engine selection #45
Pull Request -
State: closed - Opened by itsknk 4 months ago
- 7 comments
#47 - prioritise thunderbolt over WIFI #41
Pull Request -
State: open - Opened by itsknk 4 months ago
- 17 comments
#46 - Bug: NVidia / CUDA not detected
Issue -
State: closed - Opened by sammcj 4 months ago
- 7 comments
#45 - Support for Intel based Macs
Issue -
State: open - Opened by namp 4 months ago
- 5 comments