llamafile: baixar versions anteriors

What's Changed
- Update llama.cpp to b10441 by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1043
- llamafile_open_zip: validate the zip entry window against the actual file size by @professor-moody in https://github.com/mozilla-ai/llamafile/pull/1039
- fix(zip): guard extra-field header read before bounds are known by @shoemoney in https://github.com/mozilla-ai/llamafile/pull/1044
- fix(build): add missing link recipes for llama-bench, quantize, imatrix and perplexity by @dexhunter in https://github.com/mozilla-ai/llamafile/pull/1034
- fix(build): compile the ggml objects with -DNDEBUG by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1050
- Enable -DGGML_CUDA_USE_GRAPHS / -DGGML_HIP_GRAPHS by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1051
- fix(ggml): use ggml_time_init() in ggml_time_ms and ggml_time_us so that timer_freq is initialised by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1054
- Vulkan toolchain by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1055
New Contributors
- @professor-moody made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1039
- @shoemoney made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1044
- @dexhunter made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1034
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.5...0.10.6

What's Changed
0.10.5 is a release that focused on making the "sync with upstream llama.cpp" task simpler and better. In the span of 2 weeks we performed three syncs and took advantage of these iterations to improve the llamafile skill/plugin for AI agents. The result is a better process that provides more reliable code, requiring fewer iterations to go from an auto-generated draft PR to the final merged code. As a byproduct, llamafile now supports very recent models such as Ternary Bonsai 27B and Laguna-S-2.1.
Thanks to our community's contributions, this release also brings significant documentation updates clarifying the new help system, the difference between different lllamafile executables, and up-to-date llamafile GPU support. Many thanks everyone for the huge help!
- Update llama.cpp to b10052 (b2dd28a) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1021
- Update llama.cpp to b10083 (846e991) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1026
- Improve llamacpp update skill by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1027
- Update llama.cpp to b10103 (c588c4f) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1030
- docs(quickstart): clarify llamafile vs llamafile-thin and other release binaries (#1022) by @Anai-Guo in https://github.com/mozilla-ai/llamafile/pull/1023
- build(install): install transcribefile so it ships as a release artifact (#1035) by @Anai-Guo in https://github.com/mozilla-ai/llamafile/pull/1036
- Fix typo in README.md for 'architectures' by @shawntax in https://github.com/mozilla-ai/llamafile/pull/1031
- docs: Add docs for cli args and tools by @angpt in https://github.com/mozilla-ai/llamafile/pull/1037
- docs(support): document the Vulkan GPU backend (#1029) by @Anai-Guo in https://github.com/mozilla-ai/llamafile/pull/1033
New Contributors
- @shawntax made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1031
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.4...0.10.5

What's Changed
The most exciting feature that this release of llamafile brings is the first version of transcribefile! 🎉 Our transcribefile is nothing more than a cosmocc-build of the CLI tool from transcribe.cpp, @cjpais' ggml-based Speech-to-Text library that supports 16+ model families 💙 For more details, see CJ's post and Mozilla.ai's annoucement.
In addition to this, a new sync with upstream llama.cpp (which will be soon replaced by a more recent one, as I let too much time pass before the release 😬); few improvements to Vulkan and ROCm acceleration; HTTPS support (both for the server and to download models from HF given their IDs); and pledge/SECCOMP sandboxing.
Thanks everyone for improving llamafile with issues and PRs!
- Probe GPU device count out-of-process on Windows (#988 follow-up) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/994
- docs: redirect GitHub Pages docs to GitBook by @angpt in https://github.com/mozilla-ai/llamafile/pull/993
- ROCm shell script improvements by @aittalam in https://github.com/mozilla-ai/llamafile/pull/995
- docs(support): add GPU backend status table & acceleration verification (#996) by @Anai-Guo in https://github.com/mozilla-ai/llamafile/pull/997
- skill: guardrail llama.cpp update workflow with patch commands by @aittalam in https://github.com/mozilla-ai/llamafile/pull/998
- Update llama.cpp to b9747 (d6d8995) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1000
- chore: upgrade and digest pin all action digests by @RichardoC in https://github.com/mozilla-ai/llamafile/pull/1002
- CPU / GPU fixes + harness for upstream ggml's test-backend-ops by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1004
- vulkan: clearer message when --gpu vulkan is explicitly unavailable by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1006
- Fixes CTRL+C bug in chat mode by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1009
- transcribefile: CPU build of transcribe.cpp + sync to df1a4ad by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1007
- Updated runner to 16-core by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1005
- transcribefile: Metal GPU support via llamafile's runtime loader by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1010
- Add HTTPS support via cpp-httplib's mbedtls backend by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1011
- feat(help): list all accepted llama.cpp options in --help by @RichardoC in https://github.com/mozilla-ai/llamafile/pull/1003
- Bring back pledge/SECCOMP sandboxing (#930) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/1015
New Contributors
- @Anai-Guo made their first contribution in https://github.com/mozilla-ai/llamafile/pull/997
- @RichardoC made their first contribution in https://github.com/mozilla-ai/llamafile/pull/1002
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.3...0.10.4

What's Changed
This release is mainly a bugfix to a regression introduced in 0.10.2 (many many thanks to @niutech for opening the issue! 🙏)
As releases become more frequent, we are working to better automate the process and making this more open. This PR brings a new llamafile/release.sh script that's the one used to create all the new release files (we'll be testing it until the next release before updating the RELEASE.md doc).
- Update release scripts by @aittalam in https://github.com/mozilla-ai/llamafile/pull/990
- Fix uncaught SIGSEGV when GPU init fails, restore CPU fallback (#988) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/989
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.2...0.10.3

What's Changed
- Add gpu accel probe by @aittalam in https://github.com/mozilla-ai/llamafile/pull/953
- Added executable dir to list of dylib valid paths by @aittalam in https://github.com/mozilla-ai/llamafile/pull/959
- Update README with Windows executable size note by @ParthProLegend in https://github.com/mozilla-ai/llamafile/pull/962
- Update llama.cpp submodule to 7b8443ac7 by @aittalam in https://github.com/mozilla-ai/llamafile/pull/951
- Reduce cuda dylibs size by @aittalam in https://github.com/mozilla-ai/llamafile/pull/963
- Clarify Linux GPU offload diagnostics by @adminlip in https://github.com/mozilla-ai/llamafile/pull/967
- docs: rename example_llamfiles to pre-built-llamafiles for better seo by @angpt in https://github.com/mozilla-ai/llamafile/pull/972
- ggml-cpu: re-hook llamafile MoE matmul on x86 (partial fix for #973) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/974
- CPU flash-attention fixes for #975 (workaround + AVX-512 helpers + simd_gemm) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/978
- common.cpp: fix Apple Silicon physical-core detection under cosmocc (#976) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/977
- Updated version to 0.10.2 by @aittalam in https://github.com/mozilla-ai/llamafile/pull/984
- Modernise Diffusionfile Support by @cbk-res in https://github.com/mozilla-ai/llamafile/pull/970
- Update llama.cpp submodule to dbe9c0c (+ embed real web UI) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/983
New Contributors
- @ParthProLegend made their first contribution in https://github.com/mozilla-ai/llamafile/pull/962
- @adminlip made their first contribution in https://github.com/mozilla-ai/llamafile/pull/967
- @cbk-res made their first contribution in https://github.com/mozilla-ai/llamafile/pull/970
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.1...0.10.2

What's Changed
Summary:
- Added support for vulkan dylibs
- Added windows build scripts → we now have cuda, rocm, vulkan both as .so and as .dll libraries
- Updated llama.cpp submodule to 5e9c63546 → we now have llama.cpp support for new models (e.g. gemma-4, bonsai, Qwen3.6) and functionalities (e.g. llama.cpp internal tools for agents)
Details:
- Fix README_0.10.0 by @aittalam in https://github.com/mozilla-ai/llamafile/pull/918
- Add support for vulkan dylibs by @aittalam in https://github.com/mozilla-ai/llamafile/pull/892
- Add tinyblasStrsmBatched kernel by @aittalam in https://github.com/mozilla-ai/llamafile/pull/923
- Fix: GGUF Q5_1 quant crashes llamafile on aarch64 cpu by @aittalam in https://github.com/mozilla-ai/llamafile/pull/928
- fix broken link 'feel free to choose' → example llamafiles by @bquast in https://github.com/mozilla-ai/llamafile/pull/927
- Fix block-size assumption by @aittalam in https://github.com/mozilla-ai/llamafile/pull/935
- Add windows build scripts for CUDA by @aittalam in https://github.com/mozilla-ai/llamafile/pull/924
- Fix whisperfile documentation link in README by @martin0258 in https://github.com/mozilla-ai/llamafile/pull/939
- Update llama.cpp submodule to 5e9c63546 by @aittalam in https://github.com/mozilla-ai/llamafile/pull/941
- Migrate docs from MkDocs/GitHub Pages to GitBook by @angpt in https://github.com/mozilla-ai/llamafile/pull/946
- Win build improvements by @aittalam in https://github.com/mozilla-ai/llamafile/pull/940
- Fix cuda: /lib/x86_64-linux-gnu/libstdc++.so.6: version GLIBCXX_3.4.32' not found` by @aittalam in https://github.com/mozilla-ai/llamafile/pull/948
- Docs Updates by @angpt in https://github.com/mozilla-ai/llamafile/pull/949
- New release version: update version.h and docs by @aittalam in https://github.com/mozilla-ai/llamafile/pull/952
New Contributors
- @bquast made their first contribution in https://github.com/mozilla-ai/llamafile/pull/927
- @martin0258 made their first contribution in https://github.com/mozilla-ai/llamafile/pull/939
- @angpt made their first contribution in https://github.com/mozilla-ai/llamafile/pull/946
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.10.0...0.10.1

llamafile versions starting from 0.10.0 use a new build system, aimed at keeping our code more easily
aligned with the latest versions of llama.cpp. This means they support more recent models and functionalities,
but at the same time they might be missing some of the features you were accustomed to (check out this doc for a high-level description of what has been done).
If you liked the "classic experience" more, you will always be able to access the previous versions from our releases page. Our pre-built llamafiles show which version of the server they have been bundled with (0.9.* example, 0.10.* example), so you will always know which version of the software you are downloading.
What's Changed
- Accept array in chat message content field by @henfiber in https://github.com/mozilla-ai/llamafile/pull/760
- chore: Update README.md to include call for community feedback on llamafile by @njbrake in https://github.com/mozilla-ai/llamafile/pull/812
- chore: integrate whisper.cpp as a submodule by @njbrake in https://github.com/mozilla-ai/llamafile/pull/813
- chore: convert stable diffusion to submodule by @njbrake in https://github.com/mozilla-ai/llamafile/pull/818
- chore: llama.cpp as submodule by @njbrake in https://github.com/mozilla-ai/llamafile/pull/819
- feat: move docs to mkdocs by @njbrake in https://github.com/mozilla-ai/llamafile/pull/824
- chore: Add update-llama-cpp workflow. by @daavoo in https://github.com/mozilla-ai/llamafile/pull/846
- fix(update-llama-cpp): Use new_build_wip as base ref. by @daavoo in https://github.com/mozilla-ai/llamafile/pull/850
- Fixed broken llamafile URL in docs by @aittalam in https://github.com/mozilla-ai/llamafile/pull/873
- update supported OpenBSD versions by @sthen in https://github.com/mozilla-ai/llamafile/pull/897
- llamafile reloaded (v0.10.0) by @aittalam in https://github.com/mozilla-ai/llamafile/pull/867
New Contributors
- @henfiber made their first contribution in https://github.com/mozilla-ai/llamafile/pull/760
- @njbrake made their first contribution in https://github.com/mozilla-ai/llamafile/pull/812
- @daavoo made their first contribution in https://github.com/mozilla-ai/llamafile/pull/846
- @sthen made their first contribution in https://github.com/mozilla-ai/llamafile/pull/897
Full Changelog: https://github.com/mozilla-ai/llamafile/compare/0.9.3...0.10.0

This release introduces our new CLI chatbot interface. It supports multi-line input using triple quotes. It will syntax highlight Python, C, C++, Java, and JavaScript code.
This chatbot is now the default mode of operation. When you launch llamafile without any special arguments, the chatbot will be launched in the foreground, and the server will be launched in the background. You can use the --chat and --server flags to disambiguate this behavior if you only want one of them.
- a384fd7 Create ollama inspired cli chatbot
- 63205ee Add syntax highlighting to chatbot
- 7b395be Introduce new --chat flag for chatbot
- 28e98b6 Show prompt loading progress in chatbot
- 4199dae Make chat+server hybrid the new default mode
The whisperfile server now lets you upload mp3/ogg/flac.
- 74dfd21 Rewrite audio file loader code
- 7517a5f whisperfile server: convert files without ffmpeg (#568)
Other improvements have been made.
- d617c0b Added vision support to api_like_OAI (#524)
- 726f6e8 Enable gpu support in llamafile-bench (#581)
- c7c4d65 Speed up KV in llamafile-bench
- 2c940da Make replace_all() have linear complexity
- fa4c4e7 Use bf16 kv cache when it's faster
- 20fe696 Upgrade to Cosmopolitan 3.9.4
- c44664b Always favor fp16 arithmetic in tinyBLAS
- 98eff09 Quantize TriLM models using Q2_K_S (#552)