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

#6590 - couldn't remove unused layers: invalid character '\x00' looking for beginning of value

Issue - State: open - Opened by hhhaiai 17 days ago - 2 comments
Labels: bug

#6588 - Intel ARC PRO not working on Windows install.

Issue - State: closed - Opened by Solaris17 17 days ago - 1 comment
Labels: bug

#6587 - Update faq.md

Pull Request - State: open - Opened by SnoopyTlion 17 days ago - 1 comment

#6586 - Expose Tokenize and Detokenize API

Pull Request - State: open - Opened by Yurzs 18 days ago

#6584 - Add serve step to quickstart

Pull Request - State: open - Opened by anitagraser 18 days ago

#6583 - Update README.md

Pull Request - State: open - Opened by jonathanhecl 18 days ago

#6582 - adding Archyve to community integrations list

Pull Request - State: closed - Opened by nickthecook 18 days ago - 1 comment

#6581 - Add findutils to base images

Pull Request - State: closed - Opened by dhiltgen 19 days ago

#6580 - phi3.5:3.8b-mini-instruct is missing parameters on Ollama's website.

Issue - State: open - Opened by vYLQs6 19 days ago - 1 comment
Labels: bug

#6579 - fix(cmd): show info may have nil ModelInfo

Pull Request - State: closed - Opened by vimalk78 19 days ago - 1 comment

#6578 - `/show info` panics on nil ModelInfo

Issue - State: closed - Opened by vimalk78 19 days ago
Labels: bug

#6576 - libllama.so and libggml.so missing in v0.3.8 ollama-linux-arm64.tgz

Issue - State: closed - Opened by zhongTao99 19 days ago - 1 comment
Labels: bug

#6575 - no way

Issue - State: closed - Opened by Klgor1803 19 days ago - 1 comment
Labels: bug

#6574 - [Windows] Select installation location

Issue - State: closed - Opened by hecode 19 days ago - 1 comment
Labels: feature request

#6573 - Getting Error: llama runner process has terminated: exit status 127

Issue - State: closed - Opened by Blasserman 19 days ago - 2 comments
Labels: bug

#6572 - Ollama States Not Enough Video Memory When It Detects Enough

Issue - State: closed - Opened by czhang03 20 days ago - 19 comments
Labels: needs more info, memory

#6571 - Impossible to connect to ollama locally from another pc

Issue - State: closed - Opened by Wilnox23 20 days ago - 4 comments
Labels: bug

#6570 - llama: opt-in at build time

Pull Request - State: closed - Opened by dhiltgen 20 days ago - 1 comment

#6569 - TensorRT Support

Issue - State: open - Opened by JonahMMay 20 days ago - 1 comment
Labels: feature request

#6568 - Error: llama runner process has terminated: exit status 127

Issue - State: closed - Opened by MiloDev123 20 days ago - 5 comments
Labels: bug

#6567 - Improve error reporting with old or missing AMD driver on windows (unable to load amdhip64_6.dll)

Issue - State: open - Opened by Jiefei-Wang 20 days ago - 2 comments
Labels: feature request, windows, amd

#6566 - Ollama can't import safetensor of mistral 7B v0.1

Issue - State: closed - Opened by ZhoraZhang 20 days ago - 6 comments
Labels: bug

#6565 - Does ollma have the feature to save model response in log file?

Issue - State: open - Opened by keezen 20 days ago - 2 comments
Labels: feature request

#6564 - add Qwen2-VL

Issue - State: open - Opened by FelisDwan 20 days ago - 43 comments
Labels: model request

#6563 - ollama with text file?

Issue - State: closed - Opened by ayttop 20 days ago - 1 comment
Labels: feature request

#6562 - remove any unneeded build artifacts

Pull Request - State: closed - Opened by mxyng 21 days ago

#6561 - Inconsistent API Behavior

Issue - State: open - Opened by negaralizadeh 21 days ago - 2 comments
Labels: bug

#6560 - Logging final input after prompting specified in model file as a debug flag

Issue - State: closed - Opened by adela185 21 days ago - 2 comments
Labels: feature request

#6559 - Go server command line options support

Pull Request - State: closed - Opened by jessegross 21 days ago

#6558 - Multiple GPU´s Nvidia 56GB VRAM gemma2:27b

Issue - State: closed - Opened by paulopais 21 days ago - 15 comments
Labels: bug

#6556 - cuda_v12 returns poor results or crashes for Driver Version: 525.147.05

Issue - State: closed - Opened by rick-github 21 days ago
Labels: bug, nvidia

#6555 - /api/embed returns empty embeddings in docker environment

Issue - State: closed - Opened by smoothdvd 21 days ago - 1 comment
Labels: bug

#6554 - Error: llama runner process has terminated: exit status 0xc0000135

Issue - State: closed - Opened by balaji1732000 21 days ago - 4 comments
Labels: bug

#6553 - Cannot set custom folder for storing models

Issue - State: closed - Opened by anonymux1 21 days ago - 2 comments
Labels: bug

#6552 - Ollama run codestral gives Error: llama runner process has terminated

Issue - State: open - Opened by anonymux1 21 days ago - 5 comments
Labels: bug, amd

#6551 - Need cli ollama stop

Issue - State: closed - Opened by HomunMage 21 days ago - 2 comments
Labels: feature request

#6550 - Cannot download models behind a proxy in docker ollama.

Issue - State: closed - Opened by lakshmikanthgr 21 days ago - 7 comments
Labels: bug

#6549 - Ollama v0.3.8 Restart Loop

Issue - State: closed - Opened by romayojr 21 days ago - 14 comments
Labels: bug, nvidia, docker

#6548 - update the openai docs to explain how to set the context size

Pull Request - State: closed - Opened by pdevine 21 days ago

#6547 - Optimize container images for startup

Pull Request - State: open - Opened by dhiltgen 21 days ago - 1 comment

#6546 - fix(test): do not clobber models directory

Pull Request - State: closed - Opened by mxyng 22 days ago

#6545 - add llama3.1 chat template

Pull Request - State: closed - Opened by pdevine 22 days ago

#6544 - Specifying options via openai client extra_body are not handled by ollama

Issue - State: open - Opened by gaardhus 22 days ago - 3 comments
Labels: bug

#6543 - Failed to start docker without `root` access

Issue - State: open - Opened by leobenkel 22 days ago - 2 comments
Labels: bug

#6542 - Update README.md

Pull Request - State: open - Opened by rapidarchitect 22 days ago

#6541 - llama runner process has terminated: exit status127

Issue - State: closed - Opened by sosojust1984 22 days ago - 21 comments
Labels: bug

#6540 - actively retrieves the content returned from the web page

Issue - State: open - Opened by Nurburgring-Zhang 22 days ago - 1 comment
Labels: feature request

#6539 - fix: validate modelpath

Pull Request - State: closed - Opened by mxyng 22 days ago

#6538 - throw an error when encountering unsupport tensor sizes

Pull Request - State: closed - Opened by pdevine 22 days ago

#6537 - Add metrics endpoint and basic request metrics otel based

Pull Request - State: open - Opened by amila-ku 22 days ago - 2 comments

#6536 - Embeddings fixes

Pull Request - State: closed - Opened by jessegross 22 days ago

#6535 - Move ollama executable out of bin dir

Pull Request - State: closed - Opened by dhiltgen 22 days ago

#6534 - update templates to use messages

Pull Request - State: closed - Opened by mxyng 22 days ago

#6533 - /api/embeddings returning 404

Issue - State: closed - Opened by jwstanwick 22 days ago - 2 comments
Labels: bug

#6532 - add safetensors to the modelfile docs

Pull Request - State: closed - Opened by pdevine 22 days ago

#6531 - Prebuilt `ollama-linux-amd64.tgz` without cuda libs, please?

Issue - State: open - Opened by sevaseva 23 days ago - 2 comments
Labels: feature request

#6530 - fix: comment typo

Pull Request - State: closed - Opened by seankhatiri 23 days ago

#6528 - Fix import image width

Pull Request - State: closed - Opened by pdevine 23 days ago

#6527 - stella_en_400M_v5 model request

Issue - State: open - Opened by raymond-infinitecode 23 days ago - 1 comment
Labels: model request

#6526 - database modify capability

Issue - State: closed - Opened by nRanzo 23 days ago - 3 comments
Labels: feature request

#6525 - ollama collapses CPU

Issue - State: closed - Opened by Hyphaed 23 days ago - 9 comments
Labels: bug

#6524 - server: clean up route names for consistency

Pull Request - State: closed - Opened by jmorganca 23 days ago

#6523 - llama: clean up sync

Pull Request - State: closed - Opened by jmorganca 23 days ago

#6522 - detect chat template from configs that contain lists

Pull Request - State: closed - Opened by mxyng 23 days ago - 1 comment

#6521 - Go Server Fixes

Pull Request - State: closed - Opened by jessegross 23 days ago

#6520 - environmental variable not passed to service

Issue - State: closed - Opened by N4S4 24 days ago - 4 comments
Labels: bug

#6519 - Installer: Linux : Ask if unit/systemd file needs to be recreated or left alone

Issue - State: closed - Opened by jonz-secops 24 days ago - 1 comment
Labels: feature request

#6518 - Unable to run on tcp4/ipv4 on Lambda Labs instance

Issue - State: open - Opened by bayadyne 24 days ago - 2 comments
Labels: bug, needs more info

#6517 - Is Fine-Tuning Supported in Ollama?

Issue - State: closed - Opened by parthipan76 24 days ago - 1 comment
Labels: bug

#6516 - OLLAMA_NUM_PARALLEL with Gemma-2-9B model

Issue - State: closed - Opened by lihkinVerma 24 days ago - 3 comments
Labels: bug

#6515 - "ollama run qwen2" return "the resource allocation failed"

Issue - State: closed - Opened by fenggaobj 24 days ago - 6 comments
Labels: bug, nvidia

#6514 - Implicit openai model parameter multiplication disabled

Pull Request - State: closed - Opened by yaroslavyaroslav 24 days ago - 6 comments

#6513 - magnum-v2.5-12b-kto and magnum-v2-12b not running on ollama

Issue - State: open - Opened by Tuxaios 24 days ago - 8 comments
Labels: bug

#6512 - Error downloading the ollama tgz file

Issue - State: closed - Opened by CjhHa1 24 days ago - 4 comments
Labels: bug

#6510 - Performing GET request to registry.ollama.ai/v2/ returns 404 page not found

Issue - State: open - Opened by yeahdongcn 24 days ago - 3 comments
Labels: bug

#6507 - Create Blob API returned nothing

Issue - State: closed - Opened by cool-firer 24 days ago - 1 comment
Labels: bug

#6506 - Ollama with RX6600, Openwebui and win 11 support

Issue - State: closed - Opened by kevinleijh 24 days ago - 2 comments
Labels: feature request, windows, amd

#6505 - glm4 model function call support

Issue - State: open - Opened by xiaopa233 25 days ago - 10 comments
Labels: feature request, model request

#6504 - openai: increase context window when max_tokens is provided

Pull Request - State: open - Opened by jmorganca 25 days ago - 1 comment

#6503 - add integration: py-gpt

Pull Request - State: open - Opened by szczyglis-dev 25 days ago - 1 comment

#6502 - ONNX backend runtime support to simplify HW support?

Issue - State: open - Opened by TheSpaceGod 25 days ago - 3 comments
Labels: feature request

#6497 - Sync master for support MiniCPM-V 2.5 and 2.6

Pull Request - State: closed - Opened by tc-mb 25 days ago - 2 comments

#6495 - Detect running in a container

Pull Request - State: open - Opened by dhiltgen 25 days ago

#6494 - igpu

Issue - State: closed - Opened by ayttop 25 days ago - 6 comments
Labels: feature request

#6493 - Scheduler should respect main_gpu on multi-gpu setup

Issue - State: open - Opened by henryclw 26 days ago - 3 comments
Labels: bug

#6492 - Models drastically quality drop on `chat/completions` gateway

Issue - State: closed - Opened by yaroslavyaroslav 26 days ago - 7 comments
Labels: bug

#6491 - Jamba 1.5 Model

Issue - State: open - Opened by sanjibnarzary 26 days ago - 2 comments
Labels: model request

#6490 - WISPER

Issue - State: closed - Opened by DewiarQR 26 days ago - 2 comments
Labels: model request

#6489 - Error 403 occurs when I call ollama's api

Issue - State: closed - Opened by brownplayer 26 days ago - 10 comments
Labels: bug

#6488 - Ollama serve crashes with llama3.1:70b

Issue - State: open - Opened by remco-pc 26 days ago - 6 comments
Labels: bug, needs more info

#6486 - add LongWrtier Llama3.1 8b and LongWrtier GLM4 9b

Issue - State: open - Opened by Willian7004 26 days ago - 5 comments
Labels: model request

#6485 - Optimize container images for startup

Pull Request - State: closed - Opened by dhiltgen 26 days ago - 3 comments

#6484 - Only enable numa on CPUs

Pull Request - State: closed - Opened by dhiltgen 26 days ago

#6483 - gpu: Group GPU Library sets by variant

Pull Request - State: closed - Opened by dhiltgen 27 days ago