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

#5399 - Please support models of rerank type

Issue - State: open - Opened by yushengliao 3 months ago - 7 comments
Labels: model request

#5395 - CUBLAS_STATUS_ALLOC_FAILED with deepseek-coder-v2:16b

Issue - State: open - Opened by hgourvest 3 months ago - 10 comments
Labels: bug, nvidia, memory

#5394 - Ollama loads gemma2 27b with --ctx-size 16384

Issue - State: closed - Opened by chigkim 3 months ago - 1 comment
Labels: bug

#5394 - Ollama loads gemma2 27b with --ctx-size 16384

Issue - State: closed - Opened by chigkim 3 months ago - 1 comment
Labels: bug

#5393 - Inject beginning of message for assistant like "Certainly," in chat.

Issue - State: closed - Opened by chigkim 3 months ago - 6 comments
Labels: feature request

#5381 - Add Nosia to Community Integrations

Pull Request - State: open - Opened by cbldev 3 months ago - 2 comments

#5366 - docs: Add configuration docs (env vars)

Pull Request - State: closed - Opened by sammcj 3 months ago - 2 comments

#5365 - convert gemma2

Pull Request - State: open - Opened by mxyng 3 months ago - 1 comment

#5365 - convert gemma2

Pull Request - State: closed - Opened by mxyng 3 months ago - 1 comment

#5360 - Support for Snapdragon X Elite NPU & GPU

Issue - State: open - Opened by flyfox666 3 months ago - 22 comments
Labels: feature request, windows

#5356 - allow for num_ctx parameter in the openai API compatibility

Issue - State: closed - Opened by PabloRMira 3 months ago - 6 comments
Labels: feature request

#5348 - Enable grammar and JSON Schema support

Pull Request - State: open - Opened by mitar 3 months ago - 9 comments

#5341 - Gemma 2 9B and 27B is not behaving right

Issue - State: closed - Opened by jayakumark 3 months ago - 20 comments
Labels: bug

#5335 - Double text during installation

Issue - State: open - Opened by DuckyBlender 3 months ago - 1 comment
Labels: bug, wsl

#5328 - Add a `stop model` command to CLI.

Pull Request - State: closed - Opened by asdf93074 3 months ago - 3 comments

#5320 - Update faq.md

Pull Request - State: closed - Opened by Dino-Burger 3 months ago - 1 comment

#5320 - Update faq.md

Pull Request - State: closed - Opened by Dino-Burger 3 months ago - 1 comment

#5319 - Fine-tuned model responding incorrectly to my prompts

Issue - State: open - Opened by giannisak 3 months ago - 3 comments
Labels: bug

#5306 - Do not reinstall the CLI tools if they are already installed on macOS

Pull Request - State: closed - Opened by seanchristians 3 months ago - 2 comments

#5298 - Internal error at url manifests/sha256:

Issue - State: open - Opened by alexeu1994 3 months ago - 6 comments
Labels: bug

#5287 - llama: Support both old and new runners with a toggle with release build rigging

Pull Request - State: closed - Opened by dhiltgen 3 months ago - 1 comment

#5275 - ROCm on WSL

Issue - State: open - Opened by justinkb 3 months ago - 12 comments
Labels: feature request, amd, wsl

#5268 - Add Windows on ARM64 build instructions

Pull Request - State: open - Opened by hmartinez82 3 months ago

#5268 - Add Windows on ARM64 build instructions

Pull Request - State: open - Opened by hmartinez82 3 months ago

#5245 - Allow importing multi-file GGUF models

Issue - State: open - Opened by jmorganca 3 months ago - 2 comments
Labels: bug

#5211 - fp16 shows `quantization unknown` when running `ollama show`

Issue - State: closed - Opened by jmorganca 3 months ago - 2 comments
Labels: bug

#5211 - fp16 shows `quantization unknown` when running `ollama show`

Issue - State: closed - Opened by jmorganca 3 months ago - 2 comments
Labels: bug

#5210 - [email protected] - Add LTO

Pull Request - State: closed - Opened by cabelo 3 months ago

#5207 - add insert support to generate endpoint

Pull Request - State: closed - Opened by mxyng 3 months ago - 5 comments

#5200 - Add support for stream_options

Issue - State: open - Opened by igo 3 months ago - 2 comments
Labels: feature request

#5193 - Correct Ollama Show Precision of Parameter

Pull Request - State: open - Opened by royjhan 3 months ago - 2 comments

#5193 - Correct Ollama Show Precision of Parameter

Pull Request - State: open - Opened by royjhan 3 months ago - 2 comments

#5190 - Remove Quotes from Parameters in Ollama Show

Pull Request - State: closed - Opened by royjhan 3 months ago - 1 comment

#5186 - AMD Ryzen NPU support

Issue - State: open - Opened by ivanbrash 3 months ago - 10 comments
Labels: feature request, amd

#5186 - AMD Ryzen NPU support

Issue - State: open - Opened by ivanbrash 3 months ago - 4 comments
Labels: feature request, amd

#5185 - florance vision model

Issue - State: open - Opened by iplayfast 3 months ago - 5 comments
Labels: model request

#5185 - florance vision model

Issue - State: open - Opened by iplayfast 3 months ago - 2 comments
Labels: model request

#5168 - Models don't respond and ollama gets stuck after long time

Issue - State: closed - Opened by luisgg98 3 months ago - 5 comments
Labels: bug

#5143 - AMD iGPU works in docker with override but not on host

Issue - State: open - Opened by smellouk 3 months ago - 21 comments
Labels: bug, amd

#5139 - Update requirements.txt

Pull Request - State: closed - Opened by dcasota 3 months ago

#5130 - add MiniCPM-Llama3-V 2.5 muiltmodal model

Issue - State: closed - Opened by green-dalii 3 months ago - 2 comments
Labels: model request

#5091 - KV Cache Quantization

Issue - State: open - Opened by sammcj 3 months ago - 8 comments
Labels: feature request

#5068 - please add nvidia/Nemotron-4-340B-Instruct

Issue - State: open - Opened by gileneusz 3 months ago - 9 comments
Labels: model request

#5059 - Add Vulkan support to ollama

Pull Request - State: open - Opened by pufferffish 3 months ago - 26 comments

#5059 - Add Vulkan support to ollama

Pull Request - State: open - Opened by pufferffish 3 months ago - 22 comments

#5054 - Windows - `go generate` failing on build_cpu

Issue - State: open - Opened by JerrettDavis 3 months ago - 3 comments
Labels: bug, windows

#5049 - Cuda v12

Pull Request - State: closed - Opened by dhiltgen 3 months ago - 9 comments

#5040 - chore: add openapi 3.1 spec for public api

Pull Request - State: open - Opened by JerrettDavis 3 months ago - 1 comment

#5034 - Re-introduce the `llama` package

Pull Request - State: open - Opened by jmorganca 3 months ago

#5030 - Update README.md

Pull Request - State: open - Opened by Drlordbasil 3 months ago - 3 comments

#5026 - Can I customize OLLAMA_TMPDIR ?

Issue - State: closed - Opened by prince21000 3 months ago - 4 comments
Labels: question

#5021 - Some APIs in registry.ollama returns 404

Issue - State: open - Opened by stonezdj 3 months ago - 2 comments
Labels: bug

#4995 - Ollama GPU not loding properly

Issue - State: closed - Opened by tankvpython 3 months ago - 8 comments
Labels: question, performance

#4977 - qwen2-72b start to output gibberish at some point if i set num_ctx to 8192

Issue - State: open - Opened by Mikhael-Danilov 3 months ago - 4 comments
Labels: bug

#4958 - Cuda 12 runner

Issue - State: closed - Opened by jmorganca 3 months ago
Labels: feature request, nvidia

#4955 - Ollama should error with insufficient system memory and VRAM

Issue - State: closed - Opened by jmorganca 3 months ago - 7 comments
Labels: bug

#4943 - enable flash attention by default

Pull Request - State: closed - Opened by jmorganca 3 months ago

#4933 - Error: Pull Model Manifest - Timeout

Issue - State: closed - Opened by ulhaqi12 3 months ago - 2 comments
Labels: bug

#4920 - Update docs/tutorials/windows.md for Windows Uninstall

Issue - State: closed - Opened by Suvoo 3 months ago
Labels: documentation

#4917 - convert bert model from safetensors

Pull Request - State: open - Opened by mxyng 3 months ago - 1 comment

#4917 - convert bert model from safetensors

Pull Request - State: closed - Opened by mxyng 3 months ago - 1 comment

#4900 - MiniCPM-Llama3-V-2_5

Issue - State: open - Opened by kotaxyz 3 months ago - 19 comments
Labels: model request

#4900 - MiniCPM-Llama3-V-2_5

Issue - State: open - Opened by kotaxyz 3 months ago - 19 comments
Labels: model request

#4895 - Add "use_mmap" to environment variable

Issue - State: open - Opened by sisi399 3 months ago - 1 comment
Labels: feature request

#4861 - Jetson - "ollama run" command loads until timeout

Issue - State: open - Opened by Vassar-HARPER-Project 4 months ago - 8 comments
Labels: bug, nvidia

#4836 - llama runner process has terminated: exit status 127

Issue - State: closed - Opened by kruimol 4 months ago - 7 comments
Labels: bug, amd, needs more info, gpu

#4834 - Cannot pull models when http_proxy/HTTP_PROXY are set.

Issue - State: closed - Opened by janukarhisa 4 months ago - 1 comment
Labels: bug

#4828 - Ability to choose different installation location in Windows

Issue - State: closed - Opened by nviraj 4 months ago - 3 comments
Labels: feature request, windows

#4806 - codegemma broken on releases after v0.1.39

Issue - State: open - Opened by evertjr 4 months ago - 16 comments
Labels: bug

#4798 - The rocm driver rx7900xtx has been installed but cannot be used normally.

Issue - State: closed - Opened by HaoZhang66 4 months ago - 4 comments
Labels: amd, needs more info, gpu

#4771 - Ignoring env, being weird with env

Issue - State: closed - Opened by RealMrCactus 4 months ago - 1 comment
Labels: bug

#4764 - ollama stop [id of running model]

Issue - State: closed - Opened by mrdev023 4 months ago - 2 comments
Labels: feature request

#4732 - Unable to Change Ollama Models Directory on Linux (Rocky 9)

Issue - State: open - Opened by pykeras 4 months ago - 21 comments
Labels: bug

#4730 - llama3:8b-instruct performs much worse than llama3-8b-8192 on groq

Issue - State: open - Opened by mitar 4 months ago - 7 comments
Labels: bug

#4729 - dolphin-2.9.2-mixtral-8x22b

Issue - State: closed - Opened by psyv282j9d 4 months ago - 2 comments
Labels: model request

#4724 - empty response

Issue - State: closed - Opened by themw123 4 months ago - 5 comments
Labels: bug

#4710 - s390x build ollama : running gcc failed

Issue - State: open - Opened by woale 4 months ago - 8 comments
Labels: bug

#4701 - Quick model updates with `ollama pull`

Issue - State: closed - Opened by LaurentBonnaud 4 months ago - 5 comments
Labels: feature request

#4700 - please support minicpmv2.5

Issue - State: closed - Opened by chaoqunxie 4 months ago - 1 comment
Labels: model request

#4695 - codeqwen 7b q8 and fp16

Issue - State: closed - Opened by StefanIvovic 4 months ago - 1 comment
Labels: bug

#4693 - Add binary support for Nvidia Jetson Xavier- JetPack 5

Issue - State: open - Opened by ZanMax 4 months ago - 6 comments
Labels: bug, nvidia

#4670 - llama3 8b BF16 error

Issue - State: closed - Opened by ccbadd 4 months ago - 4 comments
Labels: bug, needs more info, importing

#4670 - llama3 8b BF16 error

Issue - State: closed - Opened by ccbadd 4 months ago - 4 comments
Labels: bug, needs more info, importing

#4643 - Llama.cpp now supports distributed inference across multiple machines.

Issue - State: open - Opened by AncientMystic 4 months ago - 13 comments
Labels: feature request

#4643 - Llama.cpp now supports distributed inference across multiple machines.

Issue - State: open - Opened by AncientMystic 4 months ago - 14 comments
Labels: feature request

#4632 - make cache_prompt as an option

Pull Request - State: open - Opened by Windfarer 4 months ago - 13 comments

#4625 - server/download.go: Fix downloading with too much EOF error

Pull Request - State: open - Opened by coolljt0725 4 months ago - 5 comments

#4601 - Error: llama runner process has terminated: signal: segmentation fault

Issue - State: closed - Opened by guiniao 4 months ago - 8 comments
Labels: bug

#4591 - Phi-3 Vision

Issue - State: closed - Opened by ddpasa 4 months ago - 8 comments
Labels: model request

#4545 - Ollama stops serving requests after 10-15 minutes

Issue - State: open - Opened by iganev 4 months ago - 33 comments
Labels: bug

#4521 - implement tunable registry defaults for registry and update mirrors

Pull Request - State: closed - Opened by ghost 4 months ago

#4517 - Enhanced GPU discovery and multi-gpu support with concurrency

Pull Request - State: closed - Opened by dhiltgen 4 months ago - 2 comments

#4510 - Would it be possible for Ollama to support re-rank models?

Issue - State: open - Opened by lyfuci 4 months ago - 16 comments
Labels: feature request

#4499 - paligemma

Issue - State: open - Opened by wwjCMP 4 months ago - 7 comments
Labels: model request

#4498 - Add option to disable Autoupdate

Issue - State: closed - Opened by Moulick 4 months ago - 4 comments
Labels: feature request, macos

#4494 - How to load a model from local disk path?

Issue - State: closed - Opened by quzhixue-Kimi 4 months ago - 4 comments
Labels: feature request

#4486 - Not compiled with GPU offload support

Issue - State: closed - Opened by oldgithubman 4 months ago - 20 comments
Labels: bug, needs more info

#4476 - langchain-python-rag-privategpt "Cannot submit more than 5,461 embeddings at once"

Issue - State: closed - Opened by dcasota 4 months ago - 3 comments
Labels: bug