ollama/ollama issues and pull requests

#6303 - Llama 3.1 405B fix-update

Issue - State: open - Opened by gileneusz about 1 month ago - 2 comments
Labels: model request

#6302 - Stepwise decoding via websocket, replacing server-side GBNF and JSON schema constraints

Issue - State: open - Opened by James4Ever0 about 1 month ago - 1 comment
Labels: feature request

#6301 - ollama list does not show previously downloaded models

Issue - State: open - Opened by ACodingfreak about 1 month ago - 4 comments
Labels: bug

#6300 - ollama creates a new ollama runner folder each container restart

Issue - State: closed - Opened by Minionflo about 1 month ago - 3 comments
Labels: bug, linux, docker

#6299 - Install Ollama with winget

Pull Request - State: open - Opened by nikiluk about 1 month ago

#6298 - Install Ollama with Winget on Windows

Issue - State: open - Opened by nikiluk about 1 month ago
Labels: feature request

#6297 - Models not loading when using ROCm(Radeon VII)

Issue - State: closed - Opened by WannaBeOCer about 1 month ago - 2 comments
Labels: bug, linux, amd

#6296 - Better to add athene70b f16 and q8

Issue - State: open - Opened by Llamadouble999q about 1 month ago - 2 comments
Labels: model request

#6295 - Ability to preload embedding model

Issue - State: closed - Opened by comunidadio about 1 month ago - 2 comments
Labels: feature request

#6295 - Ability to preload embedding model

Issue - State: closed - Opened by comunidadio about 1 month ago - 2 comments
Labels: feature request

#6294 - AirLLM integration?

Issue - State: open - Opened by blankuserrr about 1 month ago - 1 comment
Labels: feature request

#6293 - "The model you are attempting to pull requires a newer version of Ollama" when Ollama is built from the latest source

Issue - State: closed - Opened by sammcj about 1 month ago - 8 comments
Labels: needs more info

#6266 - MSBUILD : error MSB1009: Arquivo de projeto não existe. Opção: ollama_llama_server.vcxproj llm\generate\generate_windows.go:3: running "powershell": exit status 1

Issue - State: open - Opened by insinfo about 1 month ago - 2 comments
Labels: bug, windows

#6265 - Not a feature request, not a bug, problem with LLama3.1

Issue - State: closed - Opened by airdogvan about 1 month ago - 8 comments
Labels: feature request

#6264 - Parse cpuinfo and set default threads

Pull Request - State: open - Opened by dhiltgen about 1 month ago

#6263 - Pull Command Parsing Not Working

Issue - State: closed - Opened by chadwickhar08 about 1 month ago - 6 comments
Labels: bug, windows

#6262 - Batch embeddings get progressively worse with larger batches

Issue - State: open - Opened by jorgetrejo36 about 1 month ago - 14 comments
Labels: bug

#6261 - Offload a model command

Issue - State: closed - Opened by stavsap about 1 month ago - 5 comments
Labels: feature request

#6260 - llama3.1 memory

Pull Request - State: open - Opened by mxyng about 1 month ago - 3 comments

#6259 - Inference fails with "llama_get_logits_ith: invalid logits id 7, reason: no logits"

Issue - State: closed - Opened by yurivict about 1 month ago - 9 comments
Labels: bug

#6257 - Wrong output with the new Llama3.1 and llama3-groq-tool-use pull

Issue - State: closed - Opened by Goekdeniz-Guelmez about 1 month ago - 22 comments
Labels: bug

#6256 - Why the output of generate api is different with 'num_gpu': 0

Issue - State: closed - Opened by QuanZeng about 1 month ago - 5 comments
Labels: bug

#6255 - Update LLaVA to LLaVA OneVision

Issue - State: open - Opened by alexrah about 1 month ago - 4 comments
Labels: model request

#6254 - Lumina-mGPT support

Issue - State: open - Opened by Amazon90 about 1 month ago - 3 comments
Labels: model request

#6253 - When systemMessage exceeds a certain length, ollama is unable to process it.

Issue - State: open - Opened by billrenhero about 1 month ago - 4 comments
Labels: bug

#6253 - When systemMessage exceeds a certain length, ollama is unable to process it.

Issue - State: open - Opened by billrenhero about 1 month ago - 4 comments
Labels: bug

#6251 - Ollama multiuser scale

Issue - State: open - Opened by jamiabailey about 1 month ago
Labels: feature request, question

#6249 - ollama run llama3.1 command outputs nonsense

Issue - State: closed - Opened by erfan-khalaji about 1 month ago - 4 comments
Labels: bug

#6248 - Error: could not connect to ollama app, is it running?

Issue - State: closed - Opened by zzxgraph about 1 month ago - 20 comments
Labels: bug

#6247 - Store layers inside manifests consistently as values.

Pull Request - State: closed - Opened by jessegross about 1 month ago - 1 comment

#6246 - Modelfile - Customize a prompt

Issue - State: closed - Opened by LucasFreitas88 about 1 month ago - 11 comments
Labels: bug

#6243 - get api models

Pull Request - State: open - Opened by mxyng about 1 month ago

#6241 - Speech Prototype

Pull Request - State: open - Opened by royjhan about 1 month ago - 2 comments

#6240 - Not executed in gpu amd rx 6750 GRE

Issue - State: closed - Opened by 21307369 about 1 month ago - 2 comments
Labels: question

#6239 - support keep_alive in config.json

Issue - State: closed - Opened by avelican about 1 month ago - 2 comments
Labels: feature request

#6238 - Ollama server running out of memory when it didn't in previous version

Issue - State: closed - Opened by MxtAppz about 1 month ago - 7 comments
Labels: bug

#6238 - Ollama server running out of memory when it didn't in previous version

Issue - State: closed - Opened by MxtAppz about 1 month ago - 7 comments
Labels: bug

#6237 - Ollama Product Stance on Grammar Feature / Outstanding PRs

Issue - State: open - Opened by Kinglord about 1 month ago - 9 comments
Labels: feature request

#6237 - Ollama Product Stance on Grammar Feature / Outstanding PRs

Issue - State: open - Opened by Kinglord about 1 month ago - 5 comments
Labels: feature request

#6236 - gpu not found in windows

Issue - State: open - Opened by showyoung about 1 month ago - 17 comments
Labels: bug, windows

#6235 - Set .png and .ico to be treated as binary files.

Pull Request - State: open - Opened by Nicholas42 about 1 month ago - 5 comments

#6233 - Strange! Each request consumes an additional 2 seconds when I used /api/embed

Issue - State: open - Opened by AlbertXu233 about 1 month ago - 5 comments
Labels: bug

#6233 - Strange! Each request consumes an additional 2 seconds when I used /api/embed

Issue - State: open - Opened by AlbertXu233 about 1 month ago - 5 comments
Labels: bug

#6232 - Experimental SYCL offload for Intel 13g (Raptor Lake w Xe-LP) not offloading

Issue - State: closed - Opened by byjrack about 1 month ago - 12 comments
Labels: bug

#6230 - Add Generate Embedding for Sparse vector

Issue - State: open - Opened by shashade2012 about 1 month ago - 3 comments
Labels: feature request

#6230 - Add Generate Embedding for Sparse vector

Issue - State: open - Opened by shashade2012 about 1 month ago - 2 comments
Labels: feature request

#6229 - ollama运行多模态大模型如llava时，不支持多张图片输入 - support multiple image inputs to llava

Issue - State: open - Opened by lyp-liu about 1 month ago
Labels: feature request

#6227 - ollama cannot start on ubuntu 22.04

Issue - State: closed - Opened by garyyang85 about 1 month ago - 9 comments
Labels: bug

#6226 - Error: unexpected EOF:

Issue - State: open - Opened by KangInKoo about 1 month ago - 10 comments
Labels: bug

#6226 - Error: unexpected EOF:

Issue - State: open - Opened by KangInKoo about 1 month ago - 6 comments
Labels: bug

#6225 - POST "/api/generate" retrun 500

Issue - State: closed - Opened by w16645395520 about 1 month ago - 3 comments
Labels: bug

#6224 - Passing result from tool calling to model

Issue - State: open - Opened by tristanMatthias about 1 month ago - 3 comments
Labels: feature request

#6220 - server: parallelize embeddings in API web handler instead of in subprocess runner

Pull Request - State: closed - Opened by jmorganca about 1 month ago - 2 comments

#6218 - fix memory

Pull Request - State: open - Opened by mxyng about 1 month ago

#6211 - Error: max retries exceeded

Issue - State: closed - Opened by igorschlum about 1 month ago - 4 comments
Labels: bug

#6209 - support for llama3 and llama3.1 uncensored

Issue - State: open - Opened by olumolu about 1 month ago - 1 comment
Labels: model request

#6204 - The Quickstart section in README is missing the 'ollama start' command

Issue - State: open - Opened by yurivict about 1 month ago - 20 comments
Labels: bug

#6201 - feat: add support for running ollama on rocm in wsl

Pull Request - State: open - Opened by evshiron about 1 month ago - 1 comment

#6199 - Ollama crashes with Deepseek-Coder-V2-Lite-Instruct

Issue - State: open - Opened by shockme about 1 month ago - 8 comments
Labels: bug

#6199 - Ollama crashes with Deepseek-Coder-V2-Lite-Instruct

Issue - State: open - Opened by shockme about 1 month ago - 3 comments
Labels: bug

#6198 - Request to Add JAIS 70B Model

Issue - State: open - Opened by umar052001 about 1 month ago - 4 comments
Labels: model request

#6196 - llm decode error: 500 Internal Server Error - detokenize doesn't handle unicode characters from server.cpp properly on windows

Issue - State: open - Opened by iBog about 1 month ago - 1 comment
Labels: bug, windows

#6195 - When I start the container with http_proxy and https_proxy configured, the ollama service will not start properly

Issue - State: closed - Opened by 0sengseng0 about 1 month ago - 4 comments
Labels: bug

GitHub / ollama/ollama issues and pull requests