Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / ollama/ollama issues and pull requests
#2677 - Questions about querying Ollama via the OpenAI API
Issue -
State: closed - Opened by dictoon 7 months ago
- 8 comments
Labels: question
#2672 - Do Ollama support multiple GPUs working simultaneously?
Issue -
State: closed - Opened by papandadj 7 months ago
- 8 comments
#2637 - Integrated AMD GPU support
Issue -
State: open - Opened by DocMAX 7 months ago
- 128 comments
Labels: feature request, amd
#2627 - Error: listen tcp 127.0.0.1:11434: bind:
Issue -
State: closed - Opened by szymonk92 7 months ago
- 11 comments
Labels: bug, windows
#2624 - Support for Tinyllava
Issue -
State: closed - Opened by oliverbob 7 months ago
- 3 comments
Labels: model request
#2595 - Conversation context no longer taken into account?
Issue -
State: closed - Opened by dictoon 7 months ago
- 14 comments
#2572 - PrivateGPT example is broken for me
Issue -
State: closed - Opened by levicki 7 months ago
- 2 comments
Labels: question
#2551 - Can we change where the models are stored in windows
Issue -
State: closed - Opened by Gyro0o 7 months ago
- 20 comments
#2519 - Windows defender alert & false-positive detection
Issue -
State: closed - Opened by allandclive 7 months ago
- 59 comments
Labels: bug, windows
#2519 - Windows defender alert & false-positive detection
Issue -
State: closed - Opened by allandclive 7 months ago
- 52 comments
Labels: bug, windows
#2503 - Support Radeon RX 5700 XT (gfx1010)
Issue -
State: open - Opened by scabros 7 months ago
- 20 comments
Labels: documentation, amd
#2486 - self extend support
Pull Request -
State: closed - Opened by cognitivetech 7 months ago
- 5 comments
#2453 - Add support for older AMD GPU gfx803, gfx802, gfx805 (e.g. Radeon RX 580, FirePro W7100)
Issue -
State: open - Opened by dhiltgen 7 months ago
- 50 comments
Labels: amd
#2415 - Provide logits or logprobs in the API
Issue -
State: open - Opened by freQuensy23-coder 7 months ago
- 10 comments
Labels: feature request
#2413 - slog gin logging
Pull Request -
State: open - Opened by mxyng 7 months ago
#2409 - ollama serve stuck
Issue -
State: closed - Opened by OnixAlgo 7 months ago
- 1 comment
#2368 - Replace `reflect` usage in option parsing
Pull Request -
State: closed - Opened by jmorganca 8 months ago
- 3 comments
#2365 - Unable to use safetensor fine tuned model deepseek to gguf with convert.py from llama.cpp
Issue -
State: closed - Opened by JesseGuerrero 8 months ago
- 3 comments
#2361 - Linux installer default path
Issue -
State: closed - Opened by arabek 8 months ago
Labels: feature request, linux, install
#2358 - Models autodelete?
Issue -
State: open - Opened by SinanAkkoyun 8 months ago
- 14 comments
Labels: needs more info
#2281 - Support GPU runners with AVX2
Issue -
State: open - Opened by hyjwei 8 months ago
- 7 comments
Labels: feature request, gpu
#2236 - :grey_question: How to get "third party models/contributors" hosted on `ollama` (other than `library`)
Issue -
State: open - Opened by adriens 8 months ago
- 6 comments
#2233 - Support building from source with CUDA CC 3.5 and 3.7 support
Pull Request -
State: open - Opened by dhiltgen 8 months ago
- 10 comments
#2194 - Change the default 11434 port?
Issue -
State: closed - Opened by CHesketh76 8 months ago
- 20 comments
#2147 - permission denied when setting OLLAMA_MODELS in service file
Issue -
State: closed - Opened by lasseedfast 8 months ago
- 9 comments
#2146 - add keep_alive to generate/chat/embedding api endpoints
Pull Request -
State: closed - Opened by pdevine 8 months ago
- 14 comments
#2132 - How to solve ConnectionError ([Errno 111] Connection refused)
Issue -
State: closed - Opened by yliu2702 8 months ago
- 26 comments
#2033 - Add Vulkan runner
Issue -
State: open - Opened by maxwell-kalin 8 months ago
- 19 comments
Labels: feature request, amd, intel, gpu
#2028 - how to remove ollama from macos?
Issue -
State: closed - Opened by artnoimann 8 months ago
- 7 comments
#2022 - List available models
Issue -
State: open - Opened by ParisNeo 8 months ago
- 11 comments
Labels: feature request, ollama.com
#2006 - Rate limit download speed on pulling new models
Issue -
State: open - Opened by donuts-are-good 8 months ago
- 49 comments
Labels: networking
#2004 - Any plans to add a queue status endpoint?
Issue -
State: open - Opened by ParisNeo 8 months ago
- 5 comments
Labels: feature request
#1890 - A way to update all downloaded models
Issue -
State: open - Opened by Zig1375 8 months ago
- 9 comments
Labels: feature request
#1863 - Ollama stuck after few runs
Issue -
State: open - Opened by jadhvank 8 months ago
- 97 comments
Labels: bug
#1863 - Ollama stuck after few runs
Issue -
State: open - Opened by jadhvank 8 months ago
- 97 comments
Labels: bug
#1808 - Add Haystack to Community integrations
Pull Request -
State: closed - Opened by anakin87 9 months ago
- 2 comments
#1756 - Older CUDA compute capability 3.5 and 3.7 support
Issue -
State: open - Opened by orlyandico 9 months ago
- 55 comments
Labels: feature request, nvidia
#1736 - Download slows to a crawl at 99%
Issue -
State: open - Opened by Pugio 9 months ago
- 73 comments
Labels: bug, networking, registry
#1730 - MLX backend
Issue -
State: open - Opened by ageorgios 9 months ago
- 15 comments
Labels: feature request
#1716 - is there a way to calculate token size?
Issue -
State: closed - Opened by ralyodio 9 months ago
- 20 comments
#1712 - Ollama version
Issue -
State: closed - Opened by xyproto 9 months ago
- 7 comments
#1701 - Create uninstall script
Issue -
State: open - Opened by vtrenton 9 months ago
- 5 comments
Labels: feature request
#1642 - Add Cache option #1573
Pull Request -
State: closed - Opened by K0IN 9 months ago
- 11 comments
#1642 - Add Cache option #1573
Pull Request -
State: closed - Opened by K0IN 9 months ago
- 10 comments
#1640 - added logprobs (`n_probs`)
Pull Request -
State: open - Opened by janpf 9 months ago
- 29 comments
#1640 - added logprobs (`n_probs`)
Pull Request -
State: open - Opened by janpf 9 months ago
- 25 comments
#1612 - Add support for RWKV
Issue -
State: open - Opened by kristianpaul 9 months ago
- 7 comments
Labels: model request
#1600 - Is there any option to unload a model from memory?
Issue -
State: closed - Opened by DanielMazurkiewicz 9 months ago
- 20 comments
#1590 - Add support for Intel Arc GPUs
Issue -
State: open - Opened by taep96 9 months ago
- 43 comments
Labels: feature request, intel
#1489 - Request for Contributor.md
Issue -
State: closed - Opened by aravindputrevu 9 months ago
- 2 comments
Labels: feature request
#1431 - [WSL 2] Exposing ollama via 0.0.0.0 on local network
Issue -
State: closed - Opened by bocklucas 10 months ago
- 11 comments
#1396 - Continuous batching support
Issue -
State: closed - Opened by Huvinesh-Rajendran-12 10 months ago
- 14 comments
#1370 - Add support for NeuralHermes-2.5-Mistral-7B
Issue -
State: closed - Opened by Aspie96 10 months ago
- 1 comment
Labels: model request
#1345 - [WISH] API for token count? faster than embeddings vector length?
Issue -
State: closed - Opened by kettoleon 10 months ago
- 10 comments
Labels: feature request
#1337 - API interface works fine, CLI returns non-descriptive error presumably due to proxy with Docker install
Issue -
State: closed - Opened by mlewis1973 10 months ago
- 8 comments
Labels: bug, needs more info
#1310 - Add SSL support
Pull Request -
State: open - Opened by rootedbox 10 months ago
- 3 comments
#1310 - Add SSL support
Pull Request -
State: open - Opened by rootedbox 10 months ago
- 3 comments
#1276 - A way to reuse ollama API with RAG app.
Issue -
State: closed - Opened by sandangel 10 months ago
- 4 comments
#1249 - An easy way to get model information?
Issue -
State: closed - Opened by jorge-menjivar 10 months ago
- 5 comments
Labels: feature request
#1237 - GPTQ / ExLlamaV2 (EXL2) quantisation
Issue -
State: open - Opened by 0xdevalias 10 months ago
- 6 comments
Labels: feature request
#1170 - Allow LLMs to Query a Database Directly
Issue -
State: closed - Opened by FaizelK 10 months ago
- 19 comments
Labels: feature request
#1168 - Support openai/whisper
Issue -
State: open - Opened by OpenWaygate 10 months ago
- 8 comments
Labels: feature request, model request
#1168 - Support openai/whisper
Issue -
State: open - Opened by OpenWaygate 10 months ago
- 8 comments
Labels: feature request, model request
#1133 - initial commit of the readline editor replacement
Pull Request -
State: closed - Opened by pdevine 10 months ago
- 2 comments
#1133 - initial commit of the readline editor replacement
Pull Request -
State: closed - Opened by pdevine 10 months ago
- 2 comments
#1130 - ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"}
Issue -
State: closed - Opened by estkae 10 months ago
- 9 comments
Labels: bug
#1102 - Ollama on FreeBSD
Issue -
State: open - Opened by eng-alameedi 10 months ago
- 45 comments
Labels: feature request
#1070 - API for models on `ollama.com`
Issue -
State: open - Opened by danemadsen 10 months ago
- 4 comments
Labels: feature request, ollama.com
#1053 - Requesting support for basic auth or API key authentication
Issue -
State: open - Opened by sebiweise 11 months ago
- 12 comments
Labels: feature request
#1016 - Are AMD GPUs supported on Intel Macs?
Issue -
State: open - Opened by J0hnny007 11 months ago
- 84 comments
Labels: question, amd, macos
#1006 - Mobile support
Issue -
State: open - Opened by mikestaub 11 months ago
- 13 comments
Labels: feature request
#990 - Run Ollama on a TPU
Issue -
State: open - Opened by coolrazor007 11 months ago
- 13 comments
Labels: feature request
#959 - k8s example
Pull Request -
State: closed - Opened by mxyng 11 months ago
- 1 comment
#941 - `digest mismatch` on download
Issue -
State: open - Opened by jmorganca 11 months ago
- 86 comments
Labels: bug
#914 - Locally-hosted library
Issue -
State: open - Opened by JDRay42 11 months ago
- 19 comments
Labels: question
#857 - Manually download and upload models
Issue -
State: closed - Opened by dawnpatrol04 11 months ago
- 12 comments
Labels: bug
#845 - Ollama Docker: Error LLama runner process has terminated
Issue -
State: closed - Opened by randywreed 11 months ago
- 39 comments
#803 - Feature request: pull multiple models with ollama pull
Issue -
State: closed - Opened by rickknowles-cognitant 11 months ago
- 3 comments
#739 - Add ability to listen on unix socket
Issue -
State: open - Opened by Sir-Photch 12 months ago
- 7 comments
Labels: feature request
#709 - Add homebrew CI configuration
Pull Request -
State: closed - Opened by xyproto 12 months ago
- 10 comments
#703 - Allow listening on all local interfaces
Issue -
State: closed - Opened by vRobM 12 months ago
- 52 comments
#696 - Offline Installation and Model Download
Issue -
State: closed - Opened by OguzcanOzdemir 12 months ago
- 10 comments
#690 - Stop Ollama
Issue -
State: closed - Opened by pmorange 12 months ago
- 45 comments
#674 - Unsupported nVidia cards still cause Cuda Toolkit/Drivers to be installed
Issue -
State: open - Opened by pdevine 12 months ago
Labels: bug, nvidia
#586 - `/api/generate` with fixed seed and temperature=0 doesn't produce deterministic results
Issue -
State: closed - Opened by jmorganca 12 months ago
- 11 comments
Labels: bug
#444 - Import / Export v1
Pull Request -
State: open - Opened by mikeroySoft about 1 year ago
- 7 comments
#335 - Model import/export
Issue -
State: open - Opened by mikeroySoft about 1 year ago
- 24 comments
Labels: feature request
#335 - Model import/export
Issue -
State: open - Opened by mikeroySoft about 1 year ago
- 24 comments
Labels: feature request
#330 - ollama pull llama2:70b stuck
Issue -
State: closed - Opened by sarvagnan about 1 year ago
- 13 comments
Labels: bug
#162 - Don't automatically start on startup / have an option to disable this
Issue -
State: open - Opened by gregsadetsky about 1 year ago
- 10 comments
Labels: feature request
#156 - Fine-tuning support
Issue -
State: open - Opened by shrikrishnaholla about 1 year ago
- 16 comments
Labels: feature request
#100 - skip files in the list if we can't get the correct model path
Pull Request -
State: closed - Opened by pdevine about 1 year ago
#99 - fix mkdir blob path
Pull Request -
State: closed - Opened by mxyng about 1 year ago
#98 - First stab at a modelfile doc
Pull Request -
State: closed - Opened by technovangelist about 1 year ago
#97 - add new list command
Pull Request -
State: closed - Opened by pdevine about 1 year ago
#96 - add modelpaths
Pull Request -
State: closed - Opened by pdevine about 1 year ago
#95 - Some simple modelfile examples
Pull Request -
State: closed - Opened by technovangelist about 1 year ago
#94 - stop condition
Pull Request -
State: closed - Opened by mxyng about 1 year ago
- 1 comment
#93 - separate prompt into template and system
Pull Request -
State: closed - Opened by mxyng about 1 year ago
#92 - Create model spinner
Pull Request -
State: closed - Opened by mxyng about 1 year ago