v0.5.5

What's Changed

• Add perplexity subcommand to RamaLama CLI by @ericcurtin in #637
• throwing an exception with there is a failure in http_client.init by @jhjaggars in #647
• Add container image to support Intel ARC GPU by @cgruver in #644
• Guide users to install huggingface-cli to login to huggingface by @pbabinca in #645
• Update intel-gpu Containerfile to reduce the size of the builder image by @cgruver in #657
• Look for configs also in /usr/local/share/ramalama by @jistr in #672
• remove ro as an option when mounting images by @kush-gupt in #676
• Add generated man pages for section 7 into gitignore by @jistr in #673
• Revert "Added --jinja to llama-run command" by @ericcurtin in #683
• Pull the source model if it isn't already in local storage for the convert and push functions by @kush-gupt in #680
• bump llama.cpp to latest release hash aa6fb13 by @maxamillion in #692
• Introduce a mode so one call install from git by @ericcurtin in #690
• Add ramalama gpu_detector by @dougsland in #670
• Bump to v0.5.5 by @rhatdan in #701

New Contributors

• @cgruver made their first contribution in #644
• @pbabinca made their first contribution in #645
• @jistr made their first contribution in #672
• @kush-gupt made their first contribution in #676
• @maxamillion made their first contribution in #692
• @dougsland made their first contribution in #670

Full Changelog: v0.5.4...v0.5.5

v0.5.4

What's Changed

• Attempt to install podman by @ericcurtin in #621
• Introduce ramalama bench by @ericcurtin in #620
• Add man page for cuda support by @rhatdan in #623
• Less verbose output by @ericcurtin in #624
• Avoid dnf install on OSTree system by @ericcurtin in #622
• Fix list in README - Credits section by @kubealex in #627
• added mac cpu only support by @bmahabirbu in #628
• Added --jinja to llama-run command by @engelmi in #625
• Update llama.cpp version by @ericcurtin in #630
• Add shortname for deepseek by @rhatdan in #631
• fixed rocm detection by adding gfx targets in containerfile by @bmahabirbu in #632
• Point macOS users to script install by @kubealex in #635
• Update docker.io/nvidia/cuda Docker tag to v12.8.0 by @renovate in #633
• feat: add argument to define amd gpu targets by @jobcespedes in #634
• Bump to v0.5.4 by @rhatdan in #641

New Contributors

• @kubealex made their first contribution in #627
• @engelmi made their first contribution in #625
• @jobcespedes made their first contribution in #634

Full Changelog: v0.5.3...v0.5.4

v0.5.3

What's Changed

• We no longer have python dependancies by @ericcurtin in #588
• container_build.sh works on MAC by @rhatdan in #590
• Added vllm cuda support by @bmahabirbu in #582
• Remove omlmd from OCI calls by @rhatdan in #591
• Build with curl support by @pepijndevos in #595
• Add model transport info to ramalama run/serve manpage by @rhatdan in #593
• Various README.md updates by @ericcurtin in #600
• code crashes for rocm added proper type cast for env var by @bmahabirbu in #602
• ROCm build broken by @ericcurtin in #605
• Cleaner output if a machine executes this command by @ericcurtin in #604
• Update to version that has command history by @ericcurtin in #603
• Remove these lines they are unused by @ericcurtin in #606
• Had to make this change for my laptop to suppor nvidia by @rhatdan in #609
• Start making vllm work with RamaLama by @rhatdan in #610
• Treat hf.co/ prefix the same as hf:// by @ericcurtin in #612
• We need the rocm libraries in here by @ericcurtin in #613
• A couple of cleanups in build_llama_and_whisper.sh by @rhatdan in #615
• Bump to v0.5.3 by @rhatdan in #614

New Contributors

• @pepijndevos made their first contribution in #595

Full Changelog: v0.5.2...v0.5.3

v0.5.2

What's Changed

• This is all dead code which isn't called by @ericcurtin in #574
• On ARM by default turn on GPU acceleration by @ericcurtin in #573
• Capitalize constants in python files (CONSTANT_CASE) by @swarajpande5 in #579
• Add flake by @jim3692 in #581
• Update llama.cpp to include minor llama-run by @ericcurtin in #580
• Simplify this comparison by @ericcurtin in #576
• Fix ramalama run on docker to work correctly by @rhatdan in #583
• granite-code models in Ollama are malformed by @ericcurtin in #584
• Bump to v0.5.2 by @rhatdan in #585

New Contributors

• @jim3692 made their first contribution in #581

Full Changelog: v0.5.1...v0.5.2

v0.5.1

What's Changed

• When it debug mode show the exception for subcommand missing by @rhatdan in #568
• Revert "If podman machine is running use containers" by @ericcurtin in #570
• Check all files are adding to packaging by @ericcurtin in #569
• Add podman info or docker info to ramalama info output by @rhatdan in #567
• Bump to v0.5.1 by @rhatdan in #571

Full Changelog: v0.5.0...v0.5.1

v0.5.0

What's Changed

• Remove some more gfx9 stuff by @ericcurtin in #554
• Only use the X/Y parts of the version when pulling images by @rhatdan in #555
• If podman machine is running use containers by @ericcurtin in #557
• Update llama.cpp to contain llama-run fix by @ericcurtin in #556
• We are passing the same value in twice, causes exception by @rhatdan in #558
• Remove firefox from builds by @ericcurtin in #561
• Remove cruft added to redirect llama-cli 2>/dev/null by @rhatdan in #559
• run_cmd to exec_cmd by @ericcurtin in #564
• smollm:135m for testing purposes by @ericcurtin in #563
• Fix podman stop --all by @rhatdan in #562
• Bump to v0.5.0 by @rhatdan in #565

Full Changelog: v0.4.0...v0.5.0

v0.4.0

What's Changed

• ramalama rm should require at least one argument by @rhatdan in #516
• Fix handling of missing args for login/logout by @rhatdan in #517
• Add --version and fix sort order of commands by @rhatdan in #518
• Update shortnames.conf to alias new granite models by @ericcurtin in #519
• Prettify and improve download bars during model pulls by @swarajpande5 in #521
• Remove tqdm dependency by @swarajpande5 in #523
• Relocate File and HttpClient to their respective modules by @swarajpande5 in #522
• Add missing files to install.sh script by @ericcurtin in #524
• Change pip to pipx in installation instructions by @ericcurtin in #520
• Pass ASAHI, CUDA, HIP, HSA prefixed env vars to container by @abn in #526
• Resolves - Debug option shows traceback when no subcommand is passed by @pghole in #527
• Skip codespell of venv by adding --skip in the command by @swarajpande5 in #528
• Improved command handling and refactoring by @ericcurtin in #531
• Update README and model.py for Nvidia GPU support by @ericcurtin in #530
• Add UI support documentation by @ericcurtin in #529
• Add llama-run by @ericcurtin in #452
• Update container images to use latest by @ericcurtin in #534
• Update llama.cpp to get context size fix by @ericcurtin in #538
• If runtime is vllm, use image from modh quay.io by @ericcurtin in #533
• Remove huggingface warning by @ericcurtin in #540
• When using podman run add --pull=newer to update container image by @rhatdan in #541
• Build to build_rm by @ericcurtin in #543
• whisper.cpp now installs properly by @rhatdan in #544
• Re-add mkdir -p by @ericcurtin in #545
• This might temporarily fix an issue we are having by @ericcurtin in #547
• Attempt to use versioned container by @ericcurtin in #537
• Fix llama-run to be installed with correct library paths. by @rhatdan in #549
• Add CPU inferencing container build steps to CI by @ericcurtin in #551
• This should save some space by @ericcurtin in #552
• Bump to v0.4.0 by @rhatdan in #550

New Contributors

• @abn made their first contribution in #526
• @pghole made their first contribution in #527

Full Changelog: v0.3.0...v0.4.0

v0.3.0

What's Changed

• Move man page README.md to full links by @rhatdan in #483
• Allow users to set ctx-size via command line by @rhatdan in #484
• Add --seed option by @rhatdan in #485
• Update install.sh by @jtligon in #493
• Take in fixes from @Churchyard to modernize spec file by @smooge in #494
• Fix up building and pushing OCI Images by @rhatdan in #492
• Fix handling of file_not_found errors by @rhatdan in #499
• Updated nv docs to align with latest WSL2 cuda setup by @bmahabirbu in #503
• Add ramalama convert command by @rhatdan in #500
• Stop checking if command is running in container by @rhatdan in #505
• Add initial CONTRIBUTING.md file by @rhatdan in #507
• Place image name just before command by @ericcurtin in #511
• Simplify install by @ericcurtin in #510
• Fix handling of README.md in docs directory by @rhatdan in #512
• Add installation steps for Podman 5 in CI workflows by @ericcurtin in #508
• Bump to v0.3.0 by @rhatdan in #513

New Contributors

• @jtligon made their first contribution in #493

Full Changelog: v0.2.0...v0.3.0

v0.2.0

What's Changed

• Packit: enable fedora downstream jobs by @lsm5 in #480
• Bump to v0.2.0 by @rhatdan in #481
  Failover to OCI when push fails with default push mechanism by @rhatdan in #476
  Fall back to huggingface-cli when pulling via URL fails by @rhatdan in #475
  Full Changelog: v0.1.3...v0.2.0

v0.1.3

What's Changed

• Enable GCC Toolet 12 to support AVX VNNI by @nzwulfin in #473
• Failover to OCI when push fails with default push mechanism by @rhatdan in #476
• Fall back to huggingface-cli when pulling via URL fails by @rhatdan in #475
• Revert "Switch to llama-simple-chat" by @rhatdan in #477
• Add support for http, https and file pulls by @rhatdan in #463
• Bump to v0.1.3 by @rhatdan in #479

New Contributors

• @nzwulfin made their first contribution in #473

Full Changelog: v0.1.2...v0.1.3