2 Releases published by 1 person

• v0.4.3

  published Nov 20, 2024

• v0.4.4

  published Nov 23, 2024

67 Pull requests merged by 55 people

• Add Observability section and OpenLIT in README

  #7811 merged Nov 24, 2024

• Add preliminary support for riscv64

  #6627 merged Nov 23, 2024

• Add ChatGPTBox and RWKV-Runner to community integrations

  #4118 merged Nov 23, 2024

• OpenAI: accept additional headers to fix CORS error

  #6910 merged Nov 23, 2024

• Add Powershell Community Tool

  #7438 merged Nov 23, 2024

• runner.go: Fix deadlock with many concurrent requests

  #7805 merged Nov 23, 2024

• server: remove out of date anonymous access check

  #7785 merged Nov 22, 2024

• tests: fix max queue integration test

  #7782 merged Nov 22, 2024

• logs: explain client aborts better

  #7783 merged Nov 22, 2024

• Be quiet when redirecting output

  #7360 merged Nov 22, 2024

• Added Local Multimodal AI Chat link to README.md

  #6931 merged Nov 22, 2024

• Update google/uuid module

  #7310 merged Nov 22, 2024

• added ollamarama-matrix to community integrations

  #7325 merged Nov 22, 2024

• Adding introduction of x-cmd/ollama module

  #5191 merged Nov 22, 2024

• Adding: OrionChat: A Web Interface for Seamless AI Conversation

  #7084 merged Nov 21, 2024

• Delete duplication code Reset()

  #7308 merged Nov 21, 2024

• docs: remove tutorials, add cloud section to community integrations

  #7784 merged Nov 21, 2024

• env.sh: cleanup unused RELEASE_IMAGE_REPO

  #6855 merged Nov 21, 2024

• Update README.md with new terminal tool ParLlama

  #5623 merged Nov 21, 2024

• Add web management tool to Community Integrations

  #7126 merged Nov 21, 2024

• Update README.md >> Extension & Plugins :Terraform AWS Ollama & Open WebUI

  #5633 merged Nov 21, 2024

• Update README.md

  #5587 merged Nov 21, 2024

• Add Nosia to Community Integrations

  #5381 merged Nov 21, 2024

• Add Spring AI library reference

  #5981 merged Nov 21, 2024

• Add a new Golang library

  #7191 merged Nov 21, 2024

• add integration: py-gpt

  #6503 merged Nov 21, 2024

• Adding reference to Promptery (Ollama client) to README.md

  #7093 merged Nov 21, 2024

• Update README.md with node-red-contrib-ollama

  #4648 merged Nov 21, 2024

• Adds Ollama Grid Search to Community integrations on README

  #4301 merged Nov 21, 2024

• Add LLPhant to README.md

  #5679 merged Nov 21, 2024

• Add autogpt integration to list of community integrations

  #6459 merged Nov 21, 2024

• Update README.md

  #5575 merged Nov 21, 2024

• Update README.md: Add Ollama-GUI to web & desktop

  #5412 merged Nov 21, 2024

• Update README.md to add Shinkai Desktop

  #4877 merged Nov 21, 2024

• docs: add OpenGPA in Readme Web & Desktop

  #5497 merged Nov 21, 2024

• Update README.md - Library - Haverscript

  #6945 merged Nov 21, 2024

• Update README.md, Terminal app "bb7"

  #7064 merged Nov 21, 2024

• Update README.md, Linux AMD ROCm area

  #7213 merged Nov 21, 2024

• Update README.md

  #7221 merged Nov 21, 2024

• Add Orbiton to the README.md file

  #7770 merged Nov 21, 2024

• fix: typo in wintray messages const

  #7705 merged Nov 21, 2024

• docs: Link to AMD guide on multi-GPU guidance

  #7744 merged Nov 21, 2024

• KV Cache Fixes

  #7767 merged Nov 20, 2024

• Add llm-axe to Community Libraries in ReadMe

  #5931 merged Nov 20, 2024

• Add Swollama links to README.md

  #7383 merged Nov 20, 2024

• feat: add vibe app to readme

  #7607 merged Nov 20, 2024

• Update README.md

  #7707 merged Nov 20, 2024

• Fix minor typo in import.md

  #7764 merged Nov 20, 2024

• Add Community Integration (Update README.md)

  #7746 merged Nov 20, 2024

• Update README.md

  #7756 merged Nov 20, 2024

• Improve crash reporting

  #7728 merged Nov 20, 2024

• expose underlying error on embedding failure

  #7743 merged Nov 20, 2024

• fix(runner): Set logits to 0 if false on Batch.Add

  #7749 merged Nov 19, 2024

• server: allow mixed-case model names on push, pull, cp, and create

  #7676 merged Nov 19, 2024

• Better error suppression when getting terminal colours

  #7739 merged Nov 19, 2024

• update the docs

  #7731 merged Nov 19, 2024

• Update README.md

  #7724 merged Nov 19, 2024

• Notify the user if systemd is not running during install

  #6693 merged Nov 18, 2024

• win: add right click menu support

  #7727 merged Nov 18, 2024

• fix index out of range on zero layer metal load

  #7696 merged Nov 18, 2024

• readme: improve Community Integrations section

  #7718 merged Nov 18, 2024

• Witsy + multi-llm-ts in README

  #7713 merged Nov 18, 2024

• Add Perfect Memory AI to community integrations

  #7431 merged Nov 17, 2024

• Added ollama-haskell library

  #7451 merged Nov 17, 2024

• feat: add VT chat app to README

  #7706 merged Nov 17, 2024

• server: fix warnings in prompt_test.go

  #7710 merged Nov 17, 2024

• docs: add customization section in linux.md

  #7709 merged Nov 17, 2024

4 Pull requests opened by 4 people

• openai: fix follow-on messages having "role": "assistant"

  #7722 opened Nov 18, 2024

• ppc64le: corrected ioctls

  #7777 opened Nov 21, 2024

• Update README.md

  #7818 opened Nov 24, 2024

• Bring ollama `fileType`s into alignment with llama.cpp.

  #7819 opened Nov 24, 2024

73 Issues closed by 35 people

• Strange output behavior between Ollama llama 3.2 11b vs lmsys deployed llama 3.2 11b

  #7809 closed Nov 24, 2024

• RISCV build Ollama git version: running gcc failed: exit status 1 /usr/bin/ld: /tmp/go-link-2984308571/000019.o: in function `_cgo_d85a20fb2d9c_Cfunc_llama_model_quantize':

  #4378 closed Nov 23, 2024

• GPU usage is not high, but the display memory is full

  #7801 closed Nov 23, 2024

• ollama hangs randomly and sometimes responds with G's

  #7766 closed Nov 23, 2024

• Not reading image files with vision models

  #7804 closed Nov 23, 2024

• Context length not being updated

  #7806 closed Nov 23, 2024

• Error: Head "https://localhost:11434/": http: server gave HTTP response to HTTPS client

  #7708 closed Nov 23, 2024

• AIDC-AI/Marco-o1

  #7808 closed Nov 23, 2024

• llama3.2-vision:90b unquantized?

  #7794 closed Nov 23, 2024

• Can't find error log

  #7786 closed Nov 23, 2024

• What splitter in documents?

  #7797 closed Nov 23, 2024

• langchain_ollama tool_calls is None

  #7799 closed Nov 23, 2024

• Models get stuck in stopping state

  #7779 closed Nov 23, 2024

• Error: POST predict: Post "http://127.0.0.1:35943/completion": EOF

  #7733 closed Nov 22, 2024

• ERROR source=runner.go:426 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"

  #7545 closed Nov 22, 2024

• Outputting the response leaves a bunch of control characters.

  #6120 closed Nov 22, 2024

• Using C# and tooling, the tools are not consistently invoked by Ollama, resulting in confusing results and responses

  #7790 closed Nov 22, 2024

• Performance Regression in Ollama 0.4.0 Compared to 0.3.14

  #7534 closed Nov 22, 2024

• Support installations in non-systemd distros

  #7332 closed Nov 21, 2024

• Ollama stuck after few runs

  #1863 closed Nov 21, 2024

• List available models

  #2022 closed Nov 21, 2024

• API for models on `ollama.com`

  #1070 closed Nov 21, 2024

• List of all available models

  #7751 closed Nov 21, 2024

• CUDA error: unspecified launch failure： current device: 0, in function ggml_backend_cuda_synchronize at ggml-cuda.cu:2508

  #7771 closed Nov 21, 2024

• Add "loaded" status in Model API

  #7780 closed Nov 21, 2024

• Ollama unloads model after ~30 seconds per message with api/chat despite setting keep_alive=-1 and setting OLLAMA_KEEP_ALIVE=-1 in Windows environment variables.

  #7773 closed Nov 21, 2024

• streaming for tools support

  #7776 closed Nov 21, 2024

• Curl Error: Trying curl request in CLI, but the response is a html

  #7772 closed Nov 21, 2024

• Update Model Intel/neural-chat

  #2662 closed Nov 21, 2024

• Support for Whisper-family models

  #7233 closed Nov 21, 2024

• Ollama pull model without internet when run with docker

  #4847 closed Nov 21, 2024

• Support Pixtral Large

  #7747 closed Nov 21, 2024

• Toolcall stream

  #7774 closed Nov 21, 2024

• What happened with the recent update?

  #7762 closed Nov 20, 2024

• Model not loaded on all GPUs for load balancing

  #7768 closed Nov 20, 2024

• error reading llm response：An existing connection was forcibly closed by the remote host.

  #6937 closed Nov 20, 2024

• Not using GPU after timeout unload of models with Docker image

  #7765 closed Nov 20, 2024

• The Way to the light

  #7759 closed Nov 20, 2024

• Performance regression for 0.4.* caused by number of input tokens

  #7717 closed Nov 20, 2024

• num_ctx does not increase context length above 2048

  #7741 closed Nov 20, 2024

• How to remove the quantization at model startup

  #7753 closed Nov 20, 2024

• Open WebUI: Server Connection Error

  #6384 closed Nov 20, 2024

• Why is the generated content missing when reader 1.5b processes html

  #7732 closed Nov 20, 2024

• armv7 support

  #1926 closed Nov 20, 2024

• Performance is decreasing

  #7740 closed Nov 19, 2024

• ollama 0.4 stops answering on granite3-dense but works with 0.3

  #7656 closed Nov 19, 2024

• gpu VRAM usage didn't recover within timeout on llama3.2-vision:90b

  #7745 closed Nov 19, 2024

• ggml_cuda_init: failed to initialize CUDA: CUDA driver version is insufficient for CUDA runtime version - driver 515.65.01

  #7666 closed Nov 19, 2024

• Installation script breaks in devcontainer with terminal color issue

  #7737 closed Nov 19, 2024

• Multi-GPU returning garbage

  #7575 closed Nov 19, 2024

• Getting no compatible GPUs were discovered yet I have gpu

  #7692 closed Nov 19, 2024

• ollama update fails to restart systemd service

  #7562 closed Nov 18, 2024

• Ollama 0.4 not using VRAM on AMD RX 7900 XTX

  #7715 closed Nov 18, 2024

• Install script not reporting issue with systemd

  #6636 closed Nov 18, 2024

• On Windows 11 pro, it does work to right click "restart to update"

  #7704 closed Nov 18, 2024

• Why can't the installation directory be modified

  #7720 closed Nov 18, 2024

• AMD graphics card encounters a memory usage exception while running on Windows 11.

  #7721 closed Nov 18, 2024

• Memory leaks after each prompt on 6.11 kernel with nvidia GPU

  #7403 closed Nov 18, 2024

• Unable to download model llama3.2-vision:11b and request update ollama.

  #7651 closed Nov 18, 2024

• Proxy does not work for ollama, but does work for curl

  #7726 closed Nov 18, 2024

• How to check the actual location where the model file is saved, and the directory queried by 'ollama list'

  #7725 closed Nov 18, 2024

• Support for 1-bit LLMs

  #7312 closed Nov 18, 2024

• Ollama fails to run with ROCm 6.2.2 in Arch packaging

  #7564 closed Nov 18, 2024

• OpenCoder's template doesn't make sense for an instruct model

  #7682 closed Nov 18, 2024

• Wrong license of the `minicpm-v` model

  #7714 closed Nov 18, 2024

• CPU overheating

  #7702 closed Nov 18, 2024

• Add Nexusflow/Athene-V2-Chat and Nexusflow/Athene-V2-Agent

  #7678 closed Nov 18, 2024

• Codestral doesn't output correct response

  #4713 closed Nov 17, 2024

• codegeex4

  #5595 closed Nov 17, 2024

• Is llava license correct (possibly should be Llama2 not Apache)?

  #4561 closed Nov 17, 2024

• Splitting layers on macOS gives incorrect output

  #3695 closed Nov 17, 2024

• Upgrading removes all models

  #5591 closed Nov 17, 2024

• My Ollama stopped working to transcribe videos.

  #5649 closed Nov 17, 2024

43 Issues opened by 40 people

• Instant closure when using shell input with piped output.

  #7820 opened Nov 24, 2024

• Missing ROCm Library Files In ollama-linux-amd64-rocm.tgz

  #7817 opened Nov 24, 2024

• I import a IQ_4XS model but get an IQ1_M

  #7816 opened Nov 24, 2024

• Any fine-tuning ways?

  #7815 opened Nov 24, 2024

• Flag to prevent infinite generation

  #7814 opened Nov 24, 2024

• Not utilizing GPU

  #7813 opened Nov 24, 2024

• fetching a list of available models for download?

  #7812 opened Nov 24, 2024

• could anyone help me? something is not work. use a special gpu

  #7810 opened Nov 23, 2024

• newer version ollama chat more slower

  #7807 opened Nov 23, 2024

• problem with ollama serve

  #7803 opened Nov 22, 2024

• minimum viable GGUF crashes server on run

  #7802 opened Nov 22, 2024

• Loosing useragent after HTTP redirect while pulling models

  #7800 opened Nov 22, 2024

• Is this a bug? (2GB model -> up to 20GB pagefile)

  #7798 opened Nov 22, 2024

• prompt truncated

  #7796 opened Nov 22, 2024

• Empty output from chat-endpoint / non-empty endpoint for non-chat endpoint

  #7795 opened Nov 22, 2024

• LLM(vision) GGUF Recommendation: Is there any LLM(vision) with great performance in GGUF format?

  #7793 opened Nov 22, 2024

• Mistral Large instruct template

  #7792 opened Nov 22, 2024

• Don't try to parse images property for non image model

  #7791 opened Nov 22, 2024

• How to prevent Ollama requests to change the running model on Ollama?

  #7789 opened Nov 22, 2024

• Ollama 0.4.3 ignores HTTPS_PROXY

  #7788 opened Nov 22, 2024

• How to update ollama desktop on windows?

  #7787 opened Nov 22, 2024

• Llama3.2 Safetensors adapter not supported?

  #7781 opened Nov 21, 2024

• tool_choice parameter

  #7778 opened Nov 21, 2024

• Request: Nexa AI Omnivision

  #7769 opened Nov 20, 2024

• Ollama on AMD CPU iGPU Windows Hack

  #7763 opened Nov 20, 2024

• High Inference Time and Limited GPU Utilization with Ollama Docker

  #7761 opened Nov 20, 2024

• qwen2.5-coder isn't utilizing the GPU

  #7760 opened Nov 20, 2024

• OLLAMA_MAX_QUEUE does not limit requests to the same model

  #7758 opened Nov 20, 2024

• Memory usage higher than LM Studio for similar model

  #7757 opened Nov 20, 2024

• Proper way to train model on my data and load into Ollama?

  #7755 opened Nov 20, 2024

• 300+mb of ram while idle

  #7754 opened Nov 20, 2024

• Support for LLaVA-o1

  #7752 opened Nov 20, 2024

• ggml.c:4044: GGML_ASSERT(view_src == NULL || data_size == 0 || data_size + view_offs <= ggml_nbytes(view_src)) failed

  #7748 opened Nov 19, 2024

• llama3.2-vision model quantization request

  #7742 opened Nov 19, 2024

• Allow passing file context for FIM tasks on /api/generate

  #7738 opened Nov 19, 2024

• SSL support (For Brave Leo AI & others)

  #7736 opened Nov 19, 2024

• docker build error

  #7735 opened Nov 19, 2024

• add a Feature : clone and duplicate model from scratch when creating new model from Modelfile to laod to gpu memory

  #7734 opened Nov 19, 2024

• Whether the model can be started by using its Id?

  #7730 opened Nov 19, 2024

• GPU radeon not used

  #7729 opened Nov 19, 2024

• Can´t use GPU at Ubuntu 22.04 without Docker - permission problems

  #7723 opened Nov 18, 2024

• Feature suggestions and development compilation environment issues

  #7716 opened Nov 18, 2024

• Large host RAM allocation when using full gpu offloading

  #7711 opened Nov 17, 2024

93 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• feat: Introduce K/V Context Quantisation (vRAM improvements)

  #6279 commented on Nov 24, 2024 • 48 new comments

• Expose GPU and basic system info

  #7262 commented on Nov 19, 2024 • 5 new comments

• Add Vulkan support to ollama

  #5059 commented on Nov 21, 2024 • 3 new comments

• [Ascend ] add ascend npu support

  #5872 commented on Nov 18, 2024 • 3 new comments

• cmd: print location of model after pushing

  #7695 commented on Nov 23, 2024 • 2 new comments

• [docs] [modelfile.md] num_predict: incorrect default value

  #7693 commented on Nov 18, 2024 • 1 new comment

• Lowercase hostname for CORS.

  #5851 commented on Nov 23, 2024 • 1 new comment

• feat: function calling on stream

  #6452 commented on Nov 21, 2024 • 1 new comment

• Vendor bump llama.cpp

  #7670 commented on Nov 22, 2024 • 0 new comments

• Don't automatically start on startup / have an option to disable this

  #162 commented on Nov 24, 2024 • 0 new comments

• Support GPU runners on CPUs without AVX

  #2187 commented on Nov 24, 2024 • 0 new comments

• Error: POST predict: Post "http://127.0.0.1:42623/completion": EOF

  #7640 commented on Nov 24, 2024 • 0 new comments

• Apple Silicone Neural Engine: Core ML model package format

  #3898 commented on Nov 24, 2024 • 0 new comments

• Potential problems with the `llm/ext_server/server.cpp` not accepting `--ubatch-size ` option

  #3554 commented on Nov 23, 2024 • 0 new comments

• Can we have the newest 1-bit model

  #2821 commented on Nov 23, 2024 • 0 new comments

• Does ollama support accelerated running on npu?

  #3004 commented on Nov 23, 2024 • 0 new comments

• Ollama is not using the 100% of RTX4000 VRAM (18 of 20GB)

  #3078 commented on Nov 22, 2024 • 0 new comments

• MLX backend

  #1730 commented on Nov 22, 2024 • 0 new comments

• ollama.service cannot create folder defined by OLLAMA_MODELS or do not run when the folder is created manually

  #2701 commented on Nov 22, 2024 • 0 new comments

• Pull Private Huggingface Model

  #7240 commented on Nov 22, 2024 • 0 new comments

• Support for Ascend NPU hardware

  #5315 commented on Nov 22, 2024 • 0 new comments

• Integration with MLFlow

  #5016 commented on Nov 22, 2024 • 0 new comments

• add Qwen2-VL

  #6564 commented on Nov 22, 2024 • 0 new comments

• molmo by allen ai support

  #6958 commented on Nov 22, 2024 • 0 new comments

• Add Tab-Enabled Autocomplete for Local Model Parameters in Ollama CLI

  #7239 commented on Nov 22, 2024 • 0 new comments

• Add support for older AMD GPU gfx803, gfx802, gfx805 (e.g. Radeon RX 580, FirePro W7100)

  #2453 commented on Nov 22, 2024 • 0 new comments

• The parameter 'keep_alive' is invalid when cpu (100%)

  #7645 commented on Nov 21, 2024 • 0 new comments

• mac Errors when running

  #7495 commented on Nov 21, 2024 • 0 new comments

• Allow Compile on older GPUs - still on CUDA 11.3

  #7615 commented on Nov 22, 2024 • 0 new comments

• feat: Support Moore Threads GPU

  #7554 commented on Nov 21, 2024 • 0 new comments

• imageproc mllama refactor

  #7537 commented on Nov 19, 2024 • 0 new comments

• build: Make target improvements

  #7499 commented on Nov 23, 2024 • 0 new comments

• boost embed endpoint

  #7424 commented on Nov 21, 2024 • 0 new comments

• runner.go: Use stable llama.cpp sampling interface

  #7368 commented on Nov 21, 2024 • 0 new comments

• FEAT: add rerank support

  #7219 commented on Nov 20, 2024 • 0 new comments

• Update README.md

  #7216 commented on Nov 21, 2024 • 0 new comments

• Fix some typos in documentation, code, code comments etc.

  #7021 commented on Nov 23, 2024 • 0 new comments

• Add support for CC v5 and v6+ multi-gpu cuda setups

  #6983 commented on Nov 23, 2024 • 0 new comments

• Bump ROCm on linux to 6.2

  #6969 commented on Nov 22, 2024 • 0 new comments

• openai: support include_usage stream option to return final usage chunk

  #6784 commented on Nov 19, 2024 • 0 new comments

• AMD integrated graphic on linux kernel 6.9.9+, GTT memory, loading freeze fix

  #6282 commented on Nov 19, 2024 • 0 new comments

• cmd/server: utilizing OS copy to transfer blobs if the server is local

  #5887 commented on Nov 21, 2024 • 0 new comments

• Make llama.cpp's cache_prompt parameter configurable

  #5760 commented on Nov 20, 2024 • 0 new comments

• Add API integration tests

  #5678 commented on Nov 23, 2024 • 0 new comments

• cobra shell completions

  #4690 commented on Nov 19, 2024 • 0 new comments

• Exposing grammar as a request parameter in completion/chat with go-side grammar validation

  #4525 commented on Nov 21, 2024 • 0 new comments

• examples: Update langchain-python-simple

  #3591 commented on Nov 21, 2024 • 0 new comments

• When I run Ollama using AMD 6750GRE 12G I get an error - gfx1031 unsupported by official ROCm on windows

  #7694 commented on Nov 19, 2024 • 0 new comments

• Ability to configure embeddings dimension size

  #651 commented on Nov 19, 2024 • 0 new comments

• Ollama CPU based don't run in a LXC (Host Kernel 6.8.4-3)

  #5532 commented on Nov 19, 2024 • 0 new comments

• GGML_ASSERT(ggml_nelements(a) == ne0*ne1*ne2) failed

  #7590 commented on Nov 19, 2024 • 0 new comments

• phi-3 small and phi-3 vision missing?

  #4646 commented on Nov 19, 2024 • 0 new comments

• Only CPU is used after rebooting

  #7669 commented on Nov 19, 2024 • 0 new comments

• Support Qwen VL

  #2874 commented on Nov 19, 2024 • 0 new comments

• Ollama Product Stance on Grammar Feature / Outstanding PRs

  #6237 commented on Nov 18, 2024 • 0 new comments

• Add Vulkan runner

  #2033 commented on Nov 18, 2024 • 0 new comments

• Linux ollama 0.4.0 custom compile for AMD ROCm fails missing ggml_rocm in go compile

  #7565 commented on Nov 18, 2024 • 0 new comments

• Basic AI test result inconsistent compared to llama.cpp

  #7232 commented on Nov 18, 2024 • 0 new comments

• Response returns 'null' for 'finish_reason'

  #7547 commented on Nov 18, 2024 • 0 new comments

• KV Cache Quantization

  #5091 commented on Nov 18, 2024 • 0 new comments

• Support Steam Deck Docker amdgpu - gfx1033

  #3243 commented on Nov 18, 2024 • 0 new comments

• Please update NuExtract to v1.5

  #7397 commented on Nov 18, 2024 • 0 new comments

• Support for BGE-Multilingual-Gemma2

  #7449 commented on Nov 18, 2024 • 0 new comments

• Role field should not be repeated in streamed response chunks

  #7626 commented on Nov 18, 2024 • 0 new comments

• `Error: file does not exist` but it exists

  #5869 commented on Nov 18, 2024 • 0 new comments

• CUDA error: out of memory - Llama 3.2 3B on laptop with 13 GB RAM

  #7673 commented on Nov 18, 2024 • 0 new comments

• Keeping the community in the loop

  #2231 commented on Nov 17, 2024 • 0 new comments

• Dynamically determine context window at runtime

  #2547 commented on Nov 17, 2024 • 0 new comments

• detect missing GPU runners and don't report incorrect GPU info/logs

  #7597 commented on Nov 17, 2024 • 0 new comments

• Unable to load images from network fileshares on Windows

  #7553 commented on Nov 17, 2024 • 0 new comments

• Error: pull model manifest: Get

  #4976 commented on Nov 21, 2024 • 0 new comments

• Support Radeon RX 5700 XT (gfx1010)

  #2503 commented on Nov 21, 2024 • 0 new comments

• Streaming for tool calls is unsupported

  #5796 commented on Nov 21, 2024 • 0 new comments

• Support Mistral's new visual model: Pixtral-12b-240910

  #6748 commented on Nov 21, 2024 • 0 new comments

• Teflon (a new part of Mesa on Linux) NPU delegate support

  #3498 commented on Nov 21, 2024 • 0 new comments

• Support `ppc64le` architecture

  #796 commented on Nov 21, 2024 • 0 new comments

• ollama doesn't seem to use my GPU after update

  #7622 commented on Nov 21, 2024 • 0 new comments

• Beam search (best of) for completion API

  #1344 commented on Nov 21, 2024 • 0 new comments

• The fine tuned codegemma model exhibits abnormal performance

  #7679 commented on Nov 21, 2024 • 0 new comments

• Support setting `num_ctx` in openai api via extra query parameter

  #7063 commented on Nov 21, 2024 • 0 new comments

• How to set the parameters to make the ollama model output more detailed and comprehensive answers?

  #4352 commented on Nov 21, 2024 • 0 new comments

• Support partial loads of LLaMA 3.2 Vision 11b on 6G GPUs

  #7509 commented on Nov 21, 2024 • 0 new comments

• Unreliable free memory resulting in models not running

  #6918 commented on Nov 21, 2024 • 0 new comments

• "server stop" and "server status" commands

  #3314 commented on Nov 20, 2024 • 0 new comments

• Clarify JSONL as the Returned Format for Streaming JSON Objects

  #7703 commented on Nov 20, 2024 • 0 new comments

• ollama_models path not working any longer

  #7090 commented on Nov 20, 2024 • 0 new comments

• 503 error after using api/generate for some time

  #7573 commented on Nov 20, 2024 • 0 new comments

• Ollama should prevent sleep when working.

  #4072 commented on Nov 20, 2024 • 0 new comments

• Add support for Intel Arc GPUs

  #1590 commented on Nov 20, 2024 • 0 new comments

• Getting Unsupported architecture error When Importing Llama-vision.

  #7581 commented on Nov 20, 2024 • 0 new comments

• Moondream2 needs an update

  #6635 commented on Nov 19, 2024 • 0 new comments

• Validation of Keys and Subkeys in Ollama API JSON Objects

  #7653 commented on Nov 19, 2024 • 0 new comments

• Support AMD GPUs on Intel Macs

  #1016 commented on Nov 19, 2024 • 0 new comments