212 Commits

Author	SHA1	Message	Date
Daniel Hiltgen	8e7be3aed1	ci: avoid unbounded parallelism (#16966) ... build-darwin has gotten very slow in the past few releases, most likely due to unbounded parallelism in the MLX build causing the builder to thrash	2026-06-30 10:49:55 -07:00
Daniel Hiltgen	570679c9e0	mlx: update and fix CUDA JIT packaging (#16871) ... Bump MLX to the latest selected upstream ref and update the MLX/imagegen wrappers and tests for the new API behavior. Fix the CUDA MLX archive so runtime NVRTC kernels work after deployment: package CUTE/CUTLASS headers, include the CUDA runtime header closure, and stage a coherent CUDA-toolkit-matched CCCL tree instead of MLX's fetched CCCL for CUDA payloads. The previous archive could build successfully but crash at runtime due to missing or incompatible JIT headers.	2026-06-24 10:36:02 -07:00
Daniel Hiltgen	89a171cc70	llm: use host Vulkan loader on Windows (#16869) ... Stop bundling the Vulkan loader and resolve the host runtime for Windows Vulkan discovery and backend dependency loading. Fixes #16677	2026-06-24 10:35:48 -07:00
Daniel Hiltgen	630882621b	llama-server followups (#16353) ... * llama-server followups Misc fixes for #16031 - Add back dropped ROCm build flag for multi-GPU support on windows - Fix amdhip64_*.dll version detection for "latest" selection - Fix embeddings API for consistent normalize behavior with prior versions * ci: set up for automated llama.cpp update testing * reduce batch for fa-disabled, and constrained vram * mlx: fix v3 load bug on m5 Imagegen was incorrectly loading v3 first. This DRYs out the loading code so imagegen gets the same new v4/v3 selection logic. * fix reload bug on embedding models * bump version * steer user how to enable iGPU when disabled	2026-06-01 10:44:21 -07:00
Daniel Hiltgen	9db4bdbad6	runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) ... * broad lint fixes to sidestep CI scope glitch * runner: Remove CGO engines, use llama-server exclusively for GGML models Remove the vendored GGML and llama.cpp backend, CGO runner, Go model implementations, and sample. llama-server (built from upstream llama.cpp via FetchContent) is now the sole inference engine for GGUF-based models. (Safetensor based models continue to run on the new MLX engine.) This allows us to more rapidly pick up new capabilities and fixes from llama.cpp as they come out. On windows this now requires recent AMD driver versions to support ROCm v7 as llama.cpp currently does not support building against v6. * llama/compat: load Ollama-format GGUFs in llama-server Squashed from upstream/jmorganca/llama-compat on 2026-04-29. Source tip: 0c33775d37. Original source commits: - 25223160d llama/compat: add in-memory shim so llama-server can load Ollama-format GGUFs - 7449b539a llm,server: route Ollama-format gemma3 blobs through llama/compat - 436f2e2b1 llama/compat: make patch-apply idempotent - 8c2c9d4c8 llama/compat: extend gemma3 handler to cover 1B and 270M blobs - 021389f7b llama/compat: shrink clip.cpp injection from 18 lines to 1 - 61b367ec2 llama/compat: shrink patch to pure call-site hooks (34 -> 20 lines) - 36049361c llama/compat: simplify shim (gemma3-tested) - 8fa664865 llama/compat: add qwen35moe text handler - db0c74530 llama/compat: add qwen35moe vision (clip) support - 2a388da77 llama/compat: split shared infra into a util TU - 9a69a17dc llama/compat: document non-public API dependencies - d0f38a915 llama/compat: add gpt-oss and lfm2 handlers - 086071822 llama/compat: add mistral3 text handler (vision TODO) - 63bde9ff7 llama/compat: add mistral3 vision (clip) support - 3a57b89d5 llama/compat: apply LLaMA RoPE permute to mistral3 vision Q/K - 99cb87439 llama/compat: add qwen35, gemma4, deepseek-ocr handlers - 2c7850dba llama/compat: add nemotron_h_moe handler (latent FFN + MTP skip) - 9e3b54225 llama/compat: add llama4 text + clip handlers - 034fee349 llama/compat: add gemma4 clip handler (gemma4v projector) - 9945c5a93 server: remove dhiltgen/* compat redirect table - 5d4539101 llama/compat: rewrite gemma4 tokenizer model to BPE - 7e0765327 llama/compat: add glm-ocr text handler + text-loader load-op hook - f1bd1a25a llama/compat: add glm-ocr clip handler (glm4v projector) - 4b5cf3420 llama/compat: collapse text-loader hook back to one new patch line - eb4ecf4fc llama/compat: extend gemma4 clip handler to gemma4a (audio) - a23a5e76f llama/compat: fix gemma4a per-block norm tensor mapping - cd2dcaff4 llama/compat: add embeddinggemma handler - 1ce8a6b26 llama/compat: add qwen3-vl + qwen2.5-vl handlers - fd98ffa1e llama/compat: add gemma3n + glm4moelite handlers - cc7bdf0bc llama/compat: handle null buft in maybe_load_tensor - 0c33775d3 llama/compat: disable mmap when load_op transforms text-side tensors * refine implementation * ci: fix windows MLX build * ci: fix windows llama-server build * ci: fix windows rocm build * ci: windows mlx tuning Shorten long-tail on build, and get OllamaSetup.exe back under 2g limit * ci: fix windows dependencies * win: fix dependency gathering * disable openmp * win: arm64 cross-compile build also DRY out CI steps * scheduler improvements * ci: improvements from #15982 * win: favor ninja for faster developer builds * win: fix build * win: fix arm64 cross-compile * win: avoid spaces in compiler path * misc discovery fixes, and bos handling * lint fixes * win: fix arm cross-compile build/CI bugs * llama.cpp update * win: handle multiple CRT dirs * vulkan: add windows iGPU detection * fix creation bugs for patched models, other refactoring work * tune batch size for better performance * ci and lint fixes * fix repeat_last_n bug * build: revamp build for better developer UX * amd, sampler, qwen3next fixes * version bump * fix mlx build * revamp GPU discovery Scanning the output of llama-server is turning out to be too error prone across llama.cpp updates, so this switches to a thin dynamic library load against the bundled GGML libraries so more details can be gathered from the API. * version bump * missing file * ci: fix cache miss on rocm build * refine vulkan dep handling * fix ps reporting bug on full GPU load * improve cmake wiring for customized local builds * version bump * docker build arg cleanup * improve windows exit error logs * fix community gemma4 support and ci flakes * fix mlx unit test * tighten up ps logic to avoid double counting fit log lines * version bump * fix ps view for full gpu layer offload * add MTP wiring for llama-server and create with GGUFs * pick best template by capabilities * version bump * ci: harden apt repos * remove unused cpu core discovery * adjust batch default logic to reduce OOMs * support larger tool calls * fix audio support, template show * qwen35 mtp patch support * flesh out dtypes * rocm deps * version bump * lint fix * block broken gfx1150 on windows * fix qwen3.5 moe mtp tensors in patch * mmproj oom fallback and vulkan on by default * qwen MTP compat fix * version bump * ci: fix WoA cross-compile * ci: workaround ui tool in cross-compile * version bump * win: enable OpenMP for CPU builds * build: improve developer UX * ci: windows path workaround for CPU build * win: fix WoA dependencies * win: fix large offset reads for mmproj patched loads * version bump * fix vulkan dup detection * add OLLAMA_IGPU_ENABLE and largely disable iGPUs by default * opt-in MTP, win large offset, integraton fixes * fix unit test scheduler interaction hang * fix multi-gpu filtering * version bump * review comments * fix thinking level * fix linux rocm ordering and granite 3.3 template * version bump * ci fix - non-shallow MLX checkout * bypass linux sysfs unit test on windows --------- Co-authored-by: jmorganca <jmorganca@gmail.com>	2026-05-29 13:35:47 -07:00
Daniel Hiltgen	42e6f56c2a	ci: speed up release builds (#15982) ... * ci: speed up release builds This should help speed things up for release. It also will help speed up local developer builds a little. * ci: dedup linux build steps and optimize * review comments	2026-05-15 14:53:15 -07:00
Daniel Hiltgen	421faa0263	mlx: fix macOS 26 target leakage in v3 metallib (#16053) ... MLX compiles the AIR objects with the requested -mmacosx-version-min, but its final metallib step invokes metal instead of metallib. With the macOS 26 SDK, that can stamp the Metal v3 library with a macOS 26 deployment target. Relink the generated AIR files with metallib before install until this is fixed upstream.	2026-05-11 16:37:57 -07:00
Patrick Devine	15e6076d79	mlx: Gemma4 MTP speculative decoding (#15980) ... This change adds support for MTP (multi-token prediction) speculative decoding for the gemma4 model family. It includes: * support for importing safetensors based gemma4 draft models with `ollama create` * a new DRAFT command in the Modelfile for specifying draft models * a --quantize-draft flag for the ollama create command to quantize the draft model * cache support for speculation * changes to the rotating cache to be able to handle MTP correctly * sampling support for draft model token prediction --------- Co-authored-by: Daniel Hiltgen <daniel@ollama.com>	2026-05-05 08:55:04 -07:00
Daniel Hiltgen	534342e7e2	Update MLX and MLX-C with threading fixes (#15845) ... * Update MLX and MLX-C * Run MLX CGO work on a locked OS thread MLX now relies on OS-thread-local execution state for streams, encoders, and caches. Add an mlxthread executor backed by runtime.LockOSThread and route runner initialization, model load, inference, status memory reads, and cleanup through the worker so Go goroutine migration cannot split MLX state across native threads. Also stop caching default MLX streams before the runner owns the thread and add worker/threaded MLX regression tests. * mlx: use common status writer * mlx: bundle missing libjaccl on arm64 Inspired by #15793 * review comments	2026-05-03 10:03:14 -07:00
Daniel Hiltgen	6b5db12aa2	mlx: remove stale x86 libmlx library (#15443) ... Fixes #15433	2026-04-08 20:51:47 -07:00
Daniel Hiltgen	8968740836	mlx: Improve M5 performance with NAX (#15345) ... * mlx: Improve M5 performance with NAX This modifies the Mac release to now have 2 builds of MLX for broader compatibility while supporting the latest M5 hardware features. NAX requires building with xcode 26.2 and targetting support only for OS v26 and up. Since we want to support older MacOS versions as well, we now need 2 different MLX builds and runtime detection logic to select the optimal version. The newer build will detect NAX missing at runtime, so it is safe to run on pre M5 macs. * mac: prevent generate on cross-compiles For some versions of Xcode, cmake builds are failing due to header problems in cross-compiling during the generate phase. Since generate is producing arch independent generated output, we can skip this during cross-compiling.	2026-04-07 08:12:24 -07:00
Daniel Hiltgen	a6b27d776b	ci: fix missing windows zip file (#14807) ... Use 7z compression (better compression rate) if found in path. That alone isn't sufficient to get us under 2G, so MLX is now split out as a discrete download. Fix CI so it will fail if artifacts fail to upload.	2026-03-12 16:14:00 -07:00
Daniel Hiltgen	10e51c5177	MLX: add header vendoring and remove go build tag (#14642) ... * prefer rocm v6 on windows Avoid building with v7 - more changes are needed * MLX: add header vendoring and remove go build tag This switches to using a vendoring approach for the mlx-c headers so that Go can build without requiring a cmake first. This enables building the new MLX based code by default. Every time cmake runs, the headers are refreshed, so we can easily keep them in sync when we bump mlx versions. Basic Windows and Linux support are verified. * ci: harden for flaky choco repo servers CI sometimes fails due to choco not actually installing cache. Since it just speeds up the build, we can proceed without. * review comments	2026-03-09 17:24:45 -07:00
Daniel Hiltgen	288077c3a3	build: smarter docker parallelism (#14653) ... Our Dockerfile leverages parallel stages for more efficient builds. However, our old parallel settings were naive and lead to under/over utilization depending on the capabilities of your build system. This change switches to using Ninja for all our docker cmake builds to leverage its smarter parallel logic. We tell Ninja to target a load of nproc so each of the build stages will share the load on the system aiming for full CPU use without oversaturation. The GPU parallelism settings are also adjusted to 4 to avoid a long-tail for the last few GPU targets as they work through the long list of GPU architectures. This also fixes the Dockerfile to move Vulkan install to just the stage that needs it instead of blocking most other GPU installs. This should speed up CI which always has a clean build cache.	2026-03-06 16:36:22 -08:00
Bruce MacDonald	9d02d1d767	install: prevent partial download script execution (#14311) ... Wrap script in main function so that a truncated partial download doesn't end up executing half a script.	2026-02-18 18:32:45 -08:00
Jeffrey Morgan	935a48ed1a	scripts: skip macOS symlink creation if already correct (#14142)	2026-02-12 12:44:42 -08:00
Daniel Hiltgen	de39e24bf7	win: progress reporting on install download (#14219) ... * win: progress reporting on install download Downloading Ollama... [#################################### ] 91% 1106.6 / 1204.2 MB * review comments	2026-02-12 12:06:56 -08:00
Daniel Hiltgen	aea316f1e9	win: add curl-style install script (#14178) ... This adds a new powershell install script suitable for running via irm https://ollama.com/install.ps1 | iex If you download the script and run '-?' it reports basic usage information, as well as usage examples for common customization options. The script is signed as part of the release process to ensure it can run on a typically configured Windows system. This does not include doc updates - we can merge those after a release ships to avoid user confusion.	2026-02-09 15:28:11 -08:00
Bruce MacDonald	7ab4ca0e7f	scripts: add macOS support to install.sh (#14060) ... Allow installing Ollama on MacOS directly from the command line. This is in line with other CLI tools and results in a more streamlined experience when the user is looking to use the CLI specifically.	2026-02-05 14:59:01 -08:00
Jeffrey Morgan	b1fccabb34	Revert "Update vendored llama.cpp to b7847" (#14061)	2026-02-03 18:39:36 -08:00
Jeffrey Morgan	ef00199fb4	Update vendor ggml code to a5bb8ba4 (#13832) ... Co-authored-by: Daniel Hiltgen <daniel@ollama.com> Co-authored-by: Gabe Goodhart <ghart@us.ibm.com> Co-authored-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>	2026-02-02 17:31:59 -08:00
Jeffrey Morgan	f3b476c592	build: add -O3 optimization to CGO flags (#13877) ... CGO_CFLAGS and CGO_CXXFLAGS were being set without optimization flags, which overrides Go's default -O2 and results in unoptimized C++ code. This caused significant performance degradation in release builds compared to local `go build` which uses the default optimization. - build_darwin.sh: add -O3 to CGO_CFLAGS and CGO_CXXFLAGS exports - Dockerfile: preserve CGO_CFLAGS/CGO_CXXFLAGS from build args instead of overwriting them - app/README.md: update documentation to include -O3	2026-01-24 10:55:38 -08:00
Daniel Hiltgen	12719b6e87	MLX - dynamic loading of mlx-c (#13735) ... * MLX - dynamic loading of mlx-c Create a wrapper layer to indirect the dependency on mlx-c so the main ollama binary does not have a load-time dependency on mlx-c, mlx, and on linux, cuda. Lazy load the library via dlopen so we can adjust the path to ensure the dependencies are found and fail gracefully if not present. * review comments * fix broken tests	2026-01-16 16:34:22 -08:00
Jeffrey Morgan	4adb9cf4bb	scripts: fix macOS auto-update signature verification failure (#13713) ... Add --norsrc flag to ditto commands when creating Ollama-darwin.zip to exclude AppleDouble resource fork files (._* files) from the archive. The mlx.metallib file has extended attributes, which causes ditto to include a ._mlx.metallib AppleDouble file in the zip. Since this file is not part of the code signature seal, macOS rejects the bundle during auto-update verification with: "a sealed resource is missing or invalid" "file added: .../._mlx.metallib" The --norsrc flag prevents ditto from preserving resource forks and extended attributes, ensuring only signed files are included in the release archive.	2026-01-14 07:48:10 -08:00
Daniel Hiltgen	e4b488a7b5	CI: dedup cuda libraries to reduce payload size (#13704)	2026-01-13 11:25:31 -08:00
Jeffrey Morgan	58e4701557	scripts: increase notarization timeout to 20m (#13697) ... The 100MB mlx.metallib file significantly increased the app bundle size, causing Apple's notarization service to timeout with the previous 10m limit.	2026-01-12 20:38:38 -08:00
Jeffrey Morgan	af7ea6e96e	x/imagegen: install mlx.metallib and fix macOS rpath handling, add mlx library directories to LD_LIBRARY_PATH (#13695) ... - Install mlx.metallib for arm64 builds (required for Metal GPU acceleration) - Apply rpath settings to all macOS builds, not just x86_64 - Add CMAKE_BUILD_WITH_INSTALL_RPATH to avoid install_name_tool errors - Update build_darwin.sh to copy, sign, and package the metallib	2026-01-12 19:03:11 -08:00
Jeffrey Morgan	8f1e0140e7	x/imagegen: fix mlx build in Dockerfile and macOS build script (#13693)	2026-01-12 15:52:43 -08:00
Daniel Hiltgen	33ee7168ba	Add experimental MLX backend and engine with imagegen support (#13648) ... * WIP - MLX backend with gemma3 * MLX: add cmake and go tag build toggles To build the new MLX backend code: cmake --preset MLX cmake --build --preset MLX --parallel cmake --install build --component MLX go build -tags mlx . Note: the main.go entrypoint for the MLX engine will change in a follow up commit. * add experimental image generation runtime * add experimental image generation runtime * MLX: wire up cuda build for linux * MLX: get dependencies correct and dedup This is still too large for a unified github artifact, but is now "correct" for the mlx_cuda_v13 directory. * fix relative link bug in dedup * Add darwin build and readme * add go build tag for mlx dependent code and wire up build_darwin.sh * lint cleanup * macos: build mlx for x86 This will be CPU only. * cuda build instructions and fix drift from mlx bump * stale comment * Delete agent helper doc * Clean up readme.md * Revise README for tokenizer clarity and details Updated README to clarify tokenizer functionality and removed correctness section. --------- Co-authored-by: jmorganca <jmorganca@gmail.com>	2026-01-08 16:18:59 -08:00
Daniel Hiltgen	34d0c55ea5	Linux: switch to zstd compression (#13651) ... With the upcoming addition of MLX, the linux bundle will exceed the maximum github artifact size of 2G. This change will bring the size back down. The install.sh changes support backwards compatibility for prior versions thus should be safe to merge concurrently with this change.	2026-01-08 15:47:32 -08:00
Daniel Hiltgen	6286d9a3a5	Enable Vulkan with a temporary opt-in setting (#12931) ... * docs: vulkan information * Revert "CI: Set up temporary opt-out Vulkan support (#12614)" This reverts commit 8b6e5baee7. * vulkan: temporary opt-in for Vulkan support Revert this once we're ready to enable by default. * win: add vulkan CI build	2025-11-12 08:40:38 -08:00
Daniel Hiltgen	d3b4b9970a	app: add code for macOS and Windows apps under 'app' (#12933) ... * app: add code for macOS and Windows apps under 'app' * app: add readme * app: windows and linux only for now * ci: fix ui CI validation --------- Co-authored-by: jmorganca <jmorganca@gmail.com>	2025-11-04 11:40:17 -08:00
Daniel Hiltgen	a4770107a6	vulkan: enable flash attention (#12937) ... Also adjusts the vulkan windows build pattern to match recent changes in other backends so incremental builds are faster.	2025-11-04 10:31:22 -08:00
Daniel Hiltgen	3258a89b6e	DRY out the runner lifecycle code (#12540) ... * DRY out the runner lifecycle code Now that discovery uses the runners as well, this unifies the runner spawning code into a single place. This also unifies GPU discovery types with the newer ml.DeviceInfo * win: make incremental builds better Place build artifacts in discrete directories so incremental builds don't have to start fresh * Adjust sort order to consider iGPUs * handle cpu inference oom scenarios * review comments	2025-10-23 11:20:02 -07:00
Daniel Hiltgen	8b6e5baee7	CI: Set up temporary opt-out Vulkan support (#12614) ... Initially Vulkan support in Ollama will require building from source. Once it is more thoroughly tested and we have fixed any critical bugs, then we can bundle Vulkan into the official binary releases.	2025-10-15 14:18:01 -07:00
Thomas Stocker	2aba569a2a	Vulkan based on #9650 (#11835) ... * implement the vulkan C backend * add support in gpu.go * add support in gen_linux.sh * it builds * fix segfault * fix compilation * fix free memory monitor * fix total memory monitor * update gpu.go * fix build * fix check_perfmon len * remove cap_get_bound check * fix vulkan handle releasing * fix build on federa 40 * fix vulkan on windows * making amdgpu work on arm achitecutre with vulkan * add x86_64 lines in VulkanGlobs and capLinuxGlobs * add aarch64 lines in vulkanGlobs and capLinuxGlobs * Fix variable name * Add vulkan build patch from @jmorganca * Sync vendored ggml to add Vulkan support * Updated dockerfile https://github.com/whyvl/ollama-vulkan/issues/7#issuecomment-2660836871 Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Installing rocm library Signed-off-by: Vadim Grinco <vadim@grinco.eu> * This version works well built based on this: https://github.com/whyvl/ollama-vulkan/issues/7#issuecomment-2660836871 Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Applied 00-fix-vulkan-building.patch Work done by McBane87 here: https://github.com/whyvl/ollama-vulkan/issues/7#issuecomment-2660836871 Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Fixed the "detached head" issues Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Merged in the right direction Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Merging the latest stable (#2) * Applied 00-fix-vulkan-building.patch * Implemented vulkan backend based on the work done by whyvl, Dts0, McBane87 and others Tested on AMD Ryzen 7 8845HS w/ Radeon 780M Graphics with ROCm disabled ``` [GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers) [GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers) [GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers) [GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers) [GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers) time=2025-03-11T13:00:40.793Z level=INFO source=gpu.go:199 msg="vulkan: load libvulkan and libcap ok" time=2025-03-11T13:00:40.877Z level=INFO source=gpu.go:421 msg="error looking up vulkan GPU memory" error="device is a CPU" time=2025-03-11T13:00:40.878Z level=WARN source=amd_linux.go:443 msg="amdgpu detected, but no compatible rocm library found. Either install rocm v6, or follow manual install instructions at https://github.com/ollama/ollama/blob/main/docs/linux.md#manual-install" time=2025-03-11T13:00:40.878Z level=WARN source=amd_linux.go:348 msg="unable to verify rocm library: no suitable rocm found, falling back to CPU" time=2025-03-11T13:00:40.879Z level=INFO source=types.go:137 msg="inference compute" id=0 library=vulkan variant="" compute=1.3 driver=1.3 name="AMD Radeon Graphics (RADV GFX1103_R1)" total="15.6 GiB" available="15.6 GiB" ``` ``` # ollama run phi4:14b >>> /set verbose Set 'verbose' mode. >>> how's it going? Hello! I'm here to help you with any questions or tasks you have. How can I assist you today? 😊 total duration: 3.341959745s load duration: 18.165612ms prompt eval count: 15 token(s) prompt eval duration: 475ms prompt eval rate: 31.58 tokens/s eval count: 26 token(s) eval duration: 2.846s eval rate: 9.14 tokens/s >>> ``` * This is no longer needed Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Fixes SIGSEGV: segmentation violation running gemma3 models on ollama 0.6.0 #21 Patch provided by McBane87 on https://github.com/whyvl/ollama-vulkan/issues/21 Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Applied 04-disable-mmap-vulkan.patch From: https://github.com/whyvl/ollama-vulkan/issues/7#issuecomment-2660836871 Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Pulled new upstream code for ggml-bulkan backend Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Merged latest ollama 0.6.2 and nasrally's Flash Attention patches (#5) * readme: add Ellama to list of community integrations (#9800) * readme: add screenpipe to community integrations (#9786) * Add support for ROCm gfx1151 (#9773) * conditionally enable parallel pipelines * sample: make mutations in transforms explicit (#9743) * updated minP to use early exit making use of sorted tokens * ml/backend/ggml: allocate memory with malloc when loading model (#9822) * runner: remove cache prompt flag from ollama runner (#9826) We do not need to bypass the prompt caching in the ollama runner yet, as only embedding models needed to bypass the prompt caching. When embedding models are implemented they can skip initializing this cache completely. * ollamarunner: Check for minBatch of context space when shifting Models can specify that a group of inputs need to be handled a single batch. However, context shifting didn't respect this and could trigger a break anyways. In this case, we should instead trigger a context shift earlier so that it occurs before the grouped batch. Note that there still some corner cases: - A long prompt that exceeds the context window can get truncated in the middle of an image. With the current models, this will result in the model not recognizing the image at all, which is pretty much the expected result with truncation. - The context window is set less than the minimum batch size. The only solution to this is to refuse to load the model with these settings. However, this can never occur with current models and default settings. Since users are unlikely to run into these scenarios, fixing them is left as a follow up. * Applied latest patches from McBane87 See this for details: https://github.com/whyvl/ollama-vulkan/issues/7#issuecomment-2708820861 Signed-off-by: Vadim Grinco <vadim@grinco.eu> * Add ability to enable flash attention on vulkan (#4) * discover: add flash attention handling for vulkan * envconfig: fix typo in config.go As part of the process some code was refactored and I added a new field FlashAttention to GpuInfo since the previous solution didn't allow for a granular check via vulkan extensions. As a side effect, this now allows for granular per-device FA support checking in other places --------- Signed-off-by: Vadim Grinco <vadim@grinco.eu> Co-authored-by: zeo <108888572+zeozeozeo@users.noreply.github.com> Co-authored-by: Louis Beaumont <louis.beaumont@gmail.com> Co-authored-by: Daniel Hiltgen <dhiltgen@users.noreply.github.com> Co-authored-by: Michael Yang <mxyng@pm.me> Co-authored-by: Parth Sareen <parth.sareen@ollama.com> Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com> Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com> Co-authored-by: Jesse Gross <jesse@ollama.com> Co-authored-by: Nikita <50599445+nasrally@users.noreply.github.com> * Revert Readme changes * Revert * Revert changes in amd_linux.go * Revert changes in amd_linux.go * Remove flashattention setting gpu.go * Revert whitespace changes in gpu.go * Revert changes in transforms_test.go * Revert changes in runner.go * Revert changes in Makefile.sync * Revert some unintented changes in Dockerfile * Revert vulkan copy changes in Dockerfile * Update Vulkan Code to de4c07f93783a1a96456a44dc16b9db538ee1618 * Fixed duplicate sync in ggml.go * Revert changes in ggml.go * Revert chnages in ggml.go * enable falsh attention on vulkan * revert remove parenthesis * fixed flash attention logic enabling * vk_check_flash_attention 0 means supported * Update gpu.go * Add vulkan to Windows Build script * Remove commented out code * Enable Vulkan Flash attention in FlashAttentionSupported * Fix logging * Update Vulkan backend to e54d41befcc1575f4c898c5ff4ef43970cead75f * Removed libcap related code libcap is not directly related to Vulkan and should be added by its own PR. It adds additional library dependencies for building and also requires users to run setcap or run ollama as root, which is not ideal for easy use * Fix Unit Test (Add Vulkan Library) * Add vulkan to TestHomogeneousGPUs Test * vulkan: get GPU ID (ollama v0.11.5) Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> * disable mmap for vulkan * Reduce Changes remove TestHomogeneousGPUs (doesn't exist on master) * Update vulkan version to the version used in llama.cpp * rename gpu patch to correct number * added Vulkan API to get correct Device UUID current UUID from pipelineCacheUUID does not match CUDA * Fix GPU ID Patch * Remove Code not in llama.cpp * modified UUID code inside ggml * Fix Patch * Copied minimal definition from vulkan header * Fix compile error in Mac Metal is preferred so we're disabling Vulkan for now * Removed unused code Fix linter error in CI * Fix patches apply * fixing lint error * Removed unneeded function call Somehow removing this call fixed the crashing when Vulkan header was removed * added missing NL * Fixed missing members in Vulkan header also added zero clear for some structs * Fixed wrong structure ID * Fixed Vulkan header More aligned with official header definition now * buildvulkanAsSeperateFunction * Vulkan on Windows Test * temporarly comment out gate to run windows task * use temporarly windows-latest for build * Commenting out other presets to build vulkan * reenable cpu * commenting out error action stop * temporarly commenting out rocm * set vulkan path * comment out cude for faster turnaround * correct vulkan install * correct vulkan silent install * fixed install command * revert debugging changes (vulkan builds on windows) * revert windows-latest * trying to build vulkan for linux * temporarly disable cuda and rocm * try again linux build * fix version * trying to fix * trying again * trying again * fix version * fixed vulkan-sdk name * try again * trying again * try without version number * try again * add some more extra * trying to use version 1.4.313 * revert debugging changes * Filter out already supported gpus * revert debug code * Use runners for GPU discovery This revamps how we discover GPUs in the system by leveraging the Ollama runner. This should eliminate inconsistency between our GPU discovery and the runners capabilities at runtime, particularly for cases where we try to filter out unsupported GPUs. Now the runner does that implicitly based on the actual device list. In some cases free VRAM reporting can be unreliable which can leaad to scheduling mistakes, so this also includes a patch to leverage more reliable VRAM reporting libraries if available. Automatic workarounds have been removed as only one GPU leveraged this, which is now documented. This GPU will soon fall off the support matrix with the next ROCm bump. Additional cleanup of the scheduler and discovery packages can be done in the future once we have switched on the new memory management code, and removed support for the llama runner. * timing info for runner * WIP - wire up Vulkan with the new engine based discovery Not a complete implementation - free VRAM is better, but not accurate on windows * fix - trust the library paths from discovery when starting runner * fix index bug * fix vulkan ids to be underlying * fix - give bootstrapping more time on slow systems * Test if Vulkan device is supported * vk_check_flash_attention is not needed (coompat2 coopmapt and scalar implementation exist) * Handle GGML_VK_VISIBLE_DEVICES * ask for supported first * win: fix CPU query buffer handling Try in a short loop until we get the size right. * test: harden integration tests for slow start If the server takes a while to start up, block tests from starting until it's online to avoid setting large timeouts in individual test cases. * gofumpt fix * fix build * merge fixes * merge fixes * fixed build * merge fixes * fixing build * fixed build * fixed formatting * fixed build * fix vulkan gpu id patch * sync llama.cpp vulkan code * update build windows script * merge fixes * fix format * fixed vulkan casing * handle igpu as gpu * improve case * print out unknown library * rturn Vulkan for vulkan library * Revert "rturn Vulkan for vulkan library" This reverts commit 690461a12fd5e93295d174c97edefb2bc33285b1. * fixed patch number * return Library Name * remvoe debug code * return integrated in vulkan backend * Return pci Properties * update patch * directly get pci proeprties without parsing * workaround for filtering devices. Correct way is to have a LibraryPosition Parameter in the deviceInfo * Revert "directly get pci proeprties without parsing" This reverts commit 8e0624851f5ed7d9f74518f574dfb422e4dd4dc2. * Set FilteredID for Environment Filtering * ROCm Library is named ROCm * revert changes in patch * Create 0028-vulkan-pci-and-memory.patch * vulkan memory patch * casing fix * Add more pci properties * Added better memory management * Added better memory managament * fixed patch * Fixed patch * FilterID creation group by library * filter out vulkan supported by other gpu * fixing deviceid compare * Vulkan Fix FA coopmat1 invalid array indexing * Use everywhere the same Vulkan Version 1.4.321.1 * Remove unneeded patch * vulkan update * sync vulkan glsl files * only use for vulkan the filteredid (numeric device number) * simplify code --------- Signed-off-by: Vadim Grinco <vadim@grinco.eu> Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> Co-authored-by: pufferffish <github@bandersnatch.anonaddy.com> Co-authored-by: KOISHI KOMEIJI FROM TOUHOU 11 <fuck> Co-authored-by: DSLstandard <qgeneral35@gmail.com> Co-authored-by: pufferffish <me@windtfw.com> Co-authored-by: yeongbba <yeongmo.lee@logpresso.com> Co-authored-by: tomaThomas <tomathomas@mailbox.org> Co-authored-by: Antoine Viallon <antoine@lesviallon.fr> Co-authored-by: Vadim Grinco <vadim@grinco.eu> Co-authored-by: zeo <108888572+zeozeozeo@users.noreply.github.com> Co-authored-by: Louis Beaumont <louis.beaumont@gmail.com> Co-authored-by: Daniel Hiltgen <dhiltgen@users.noreply.github.com> Co-authored-by: Michael Yang <mxyng@pm.me> Co-authored-by: Parth Sareen <parth.sareen@ollama.com> Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com> Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com> Co-authored-by: Jesse Gross <jesse@ollama.com> Co-authored-by: Nikita <50599445+nasrally@users.noreply.github.com> Co-authored-by: Masato Nakasaka <masato.nakasaka@intel.com> Co-authored-by: Xiaodong Ye <xiaodong.ye@mthreads.com> Co-authored-by: Daniel Hiltgen <daniel@ollama.com>	2025-10-14 10:59:58 -07:00
Daniel Hiltgen	918231931c	win: fix build script (#12513)	2025-10-06 14:46:45 -07:00
Daniel Hiltgen	55ca827267	AMD: block running on unsupported gfx900/gfx906 (#12481)	2025-10-02 16:53:05 -07:00
Daniel Hiltgen	bc8909fb38	Use runners for GPU discovery (#12090) ... This revamps how we discover GPUs in the system by leveraging the Ollama runner. This should eliminate inconsistency between our GPU discovery and the runners capabilities at runtime, particularly for cases where we try to filter out unsupported GPUs. Now the runner does that implicitly based on the actual device list. In some cases free VRAM reporting can be unreliable which can leaad to scheduling mistakes, so this also includes a patch to leverage more reliable VRAM reporting libraries if available. Automatic workarounds have been removed as only one GPU leveraged this, which is now documented. This GPU will soon fall off the support matrix with the next ROCm bump. Additional cleanup of the scheduler and discovery packages can be done in the future once we have switched on the new memory management code, and removed support for the llama runner.	2025-10-01 15:12:32 -07:00
Daniel Hiltgen	0c3d0e7533	build: avoid unbounded parallel builds (#12319) ... With the addition of cuda v13, on a clean setup, the level of parallelism was causing docker desktop to become overwhelmed and compilers were crashing. This limits to 8 parallel per build stage, with the ability to override if you have many more cores available.	2025-09-18 14:57:01 -07:00
Daniel Hiltgen	17a023f34b	Add v12 + v13 cuda support (#12000) ... * Add support for upcoming NVIDIA Jetsons The latest Jetsons with JetPack 7 are moving to an SBSA compatible model and will not require building a JetPack specific variant. * cuda: bring back dual versions This adds back dual CUDA versions for our releases, with v11 and v13 to cover a broad set of GPUs and driver versions. * win: break up native builds in build_windows.ps1 * v11 build working on windows and linux * switch to cuda v12.8 not JIT * Set CUDA compression to size * enhance manual install linux docs	2025-09-10 12:05:18 -07:00
Daniel Hiltgen	405d2f628f	ci: rocm parallel builds on windows (#11187) ... The preset CMAKE_HIP_FLAGS isn't getting used on Windows. This passes the parallel flag in through the C/CXX flags, along with suppression for some log spew warnings to quiet down the build.	2025-06-24 15:27:09 -07:00
Daniel Hiltgen	1c6669e64c	Re-remove cuda v11 (#10694) ... * Re-remove cuda v11 Revert the revert - drop v11 support requiring drivers newer than Feb 23 This reverts commit c6bcdc4223. * Simplify layout With only one version of the GPU libraries, we can simplify things down somewhat. (Jetsons still require special handling) * distinct sbsa variant for linux arm64 This avoids accidentally trying to load the sbsa cuda libraries on a jetson system which results in crashes. * temporary prevent rocm+cuda mixed loading	2025-06-23 14:07:00 -07:00
Daniel Hiltgen	c6bcdc4223	Revert "remove cuda v11 (#10569)" (#10692) ... Bring back v11 until we can better warn users that their driver is too old. This reverts commit fa393554b9.	2025-05-13 13:12:54 -07:00
Daniel Hiltgen	fa393554b9	remove cuda v11 (#10569) ... This reduces the size of our Windows installer payloads by ~256M by dropping support for nvidia drivers older than Feb 2023. Hardware support is unchanged. Linux default bundle sizes are reduced by ~600M to 1G.	2025-05-06 17:33:19 -07:00
Daniel Hiltgen	6a74bba7e7	win: ensure ollama paths come first (#10549) ... For all search path env vars make sure our dirs are first to avoid potentially finding other incompatible libraries on the users system. Also fixes a minor build script glitch for windows rocm	2025-05-03 13:11:48 -07:00
Daniel Hiltgen	2d2247e59e	Align versions for local builds (#9635) ... Darwin was using a different pattern for the version string than linux or windows.	2025-03-14 15:44:08 -07:00
Daniel Hiltgen	4dcf80167a	Build release for windows with local script (#9636)	2025-03-11 08:34:20 -07:00
Michael Yang	ba7d31240e	fix: own lib/ollama directory ... expand backend loading error handling to catch more problems and log them instead of panicing	2025-03-03 13:01:18 -08:00
Daniel Hiltgen	688925aca9	Windows ARM build (#9120) ... * Windows ARM build Skip cmake, and note it's unused in the developer docs. * Win: only check for ninja when we need it On windows ARM, the cim lookup fails, but we don't need ninja anyway.	2025-02-27 09:02:25 -08:00