ollama

Commit Graph

Author	SHA1	Message	Date
batuhankadioglu	7b68e254c2	all: update several golang.org/x packages (#10436 )	11 months ago
Parth Sareen	0682dae027	sample: improve ollama engine sampler performance (#9374 ) This change bring in various interface cleanups along with greatly improving the performance of the sampler. Tested with llama3.2 on local machine. Improves performance from ~ 70 tokens/s -> 135 tokens/s with topK(40) enabled. Without topK performance is ~ 110 tokens/s	1 year ago
Blake Mizerany	e2252d0fc6	server/internal/registry: take over pulls from server package (#9485 ) This commit replaces the old pull implementation in the server package with the new, faster, more robust pull implementation in the registry package. The new endpoint, and now the remove endpoint too, are behind the feature gate "client2" enabled only by setting the OLLAMA_EXPERIMENT environment variable include "client2". Currently, the progress indication is wired to perform the same as the previous implementation to avoid making changes to the CLI, and because the status reports happen at the start of the download, and the end of the write to disk, the progress indication is not as smooth as it could be. This is a known issue and will be addressed in a future change. This implementation may be ~0.5-1.0% slower in rare cases, depending on network and disk speed, but is generally MUCH faster and more robust than the its predecessor in all other cases.	1 year ago
Jesse Gross	e185c08ad9	go.mod: Use full version for go 1.24.0 Otherwise on Linux I get: go: download go1.24 for linux/amd64: toolchain not available	1 year ago
Blake Mizerany	2412adf42b	server/internal: replace model delete API with new registry handler. (#9347 ) This commit introduces a new API implementation for handling interactions with the registry and the local model cache. The new API is located in server/internal/registry. The package name is "registry" and should be considered temporary; it is hidden and not bleeding outside of the server package. As the commits roll in, we'll start consuming more of the API and then let reverse osmosis take effect, at which point it will surface closer to the root level packages as much as needed.	1 year ago
Blake Mizerany	4604b10306	go.mod: bump to go1.24 (#9242 )	1 year ago
Michael Yang	dcfb7a105c	next build (#8539 ) * add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install targets * remove unused files * ml: visit each library path once * build: skip cpu variants on arm * build: install cpu targets * build: fix workflow * shorter names * fix rocblas install * docs: clean up development.md * consistent build dir removal in development.md * silence -Wimplicit-function-declaration build warnings in ggml-cpu * update readme * update development readme * llm: update library lookup logic now that there is one runner (#8587) * tweak development.md * update docs * add windows cuda/rocm tests --------- Co-authored-by: jmorganca <jmorganca@gmail.com> Co-authored-by: Daniel Hiltgen <daniel@ollama.com>	1 year ago
Michael Yang	cb40d60469	chore: upgrade to gods v2 gods v2 uses go generics rather than interfaces which simplifies the code considerably	1 year ago
Squishedmac	9ab62eb96f	update golang.org/x dependencies (#8172 )	1 year ago
Blake Mizerany	a37f4a86a7	go.mod: go 1.22.8 -> 1.23.4 (#8036 )	1 year ago
Meng Zhuo	2ebdb54fb3	all: update math32 go mod to v1.11.0 (#6627 )	1 year ago
Mikel Olasagasti Uranga	597072ef1b	readme: update google/uuid module (#7310 ) update uuid.New().String() to uuid.NewString()	1 year ago
Bruce MacDonald	0679d491fe	chore(deps): bump golang.org/x dependencies (#7655 ) - golang.org/x/sync v0.3.0 -> v0.9.0 - golang.org/x/image v0.14.0 -> v0.22.0 - golang.org/x/text v0.15.0 -> v0.20.0	1 year ago
Daniel Hiltgen	abd5dfd06a	Bump to latest Go 1.22 patch (#7379 )	1 year ago
Patrick Devine	c7cb0f0602	image processing for llama3.2 (#6963 ) Co-authored-by: jmorganca <jmorganca@gmail.com> Co-authored-by: Michael Yang <mxyng@pm.me> Co-authored-by: Jesse Gross <jesse@ollama.com>	1 year ago
Daniel Hiltgen	feedf49c71	Go back to a pinned Go version Go version 1.22.6 is triggering AV false positives, so go back to 1.22.5	2 years ago
Michael Yang	fb6cbc02fb	update named templates	2 years ago
Michael Yang	9b6c2e6eb6	detect chat template from KV	2 years ago
Michael Yang	171eb040fc	simplify safetensors reading	2 years ago
Michael Yang	34d5ef29b3	fix conversion for f16 or f32 inputs	2 years ago
jmorganca	63a453554d	`go mod tidy`	2 years ago
Patrick Devine	1e1634daca	update go deps (#4324 )	2 years ago
Patrick Devine	9f8691c6c8	Add llama2 / torch models for `ollama create` (#3607 )	2 years ago
Patrick Devine	5a5efee46b	Add gemma safetensors conversion (#3250 ) Co-authored-by: Michael Yang <mxyng@pm.me>	2 years ago
Patrick Devine	1b272d5bcd	change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347 )	2 years ago
Patrick Devine	2c017ca441	Convert Safetensors to an Ollama model (#2824 )	2 years ago
Michael Yang	fc483274ad	clean up go.mod	2 years ago
vinjn	66ef308abd	Import "containerd/console" lib to support colorful output in Windows terminal	2 years ago
Daniel Hiltgen	29e90cc13b	Implement new Go based Desktop app This focuses on Windows first, but coudl be used for Mac and possibly linux in the future.	2 years ago
Daniel Hiltgen	ecbfc0182f	Go bump to v1.21 to pick up slog	2 years ago
Daniel Hiltgen	39928a42e8	Always dynamically load the llm server library This switches darwin to dynamic loading, and refactors the code now that no static linking of the library is used on any platform	2 years ago
Daniel Hiltgen	d4cd695759	Add cgo implementation for llama.cpp Run the server.cpp directly inside the Go runtime via cgo while retaining the LLM Go abstractions.	2 years ago
Patrick Devine	630518f0d9	Add unit test of API routes (#1528 )	2 years ago
Michael Yang	7232f1fa41	go mod tidy	2 years ago
Michael Yang	01ea6002c4	replace go-humanize with format.HumanBytes	2 years ago
Michael Yang	341fb7e35f	go mod tidy	2 years ago
Patrick Devine	deeac961bb	new readline library (#847 )	2 years ago
Ajay Kemparaj	bb8464c0d2	update golang.org/x/net fixes CVE-2023-3978,CVE-2023-39325,CVE-2023-44487 (#855 )	2 years ago
Bruce MacDonald	a0c3e989de	deprecate modelfile embed command (#759 )	2 years ago
Michael Yang	8544edca21	parallel chunked downloads	3 years ago
Patrick Devine	87d9efb364	switch to forked readline lib which doesn't wreck the repl prompt (#578 )	3 years ago
Michael Yang	e9f6df7dca	use slices.DeleteFunc	3 years ago
Bruce MacDonald	42998d797d	subprocess llama.cpp server (#401 ) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm	3 years ago
Michael Yang	d791df75dd	check memory requirements before loading	3 years ago
Bruce MacDonald	a6f6d18f83	embed text document in modelfile	3 years ago
Bruce MacDonald	1c5a8770ee	read runner parameter options from map - read runner options from map to see what was specified explicitly and overwrite zero values	3 years ago
Bruce MacDonald	daa0d1de7a	allow specifying zero values in modelfile	3 years ago
Michael Yang	8609db77ea	use gin-contrib/cors middleware	3 years ago
Patrick Devine	e4d7f3e287	vendor in progress bar and change to bytes instead of bibytes (#130 )	3 years ago
Michael Yang	84200dcde6	use readline	3 years ago

1 2

61 Commits (af21a5ac397c1d2ce62881e0962bbff9d6da31f2)