ollama

Commit Graph

Author	SHA1	Message	Date
Jeffrey Morgan	4458efb73a	Load all layers on `arm64` macOS if model is small enough (#2149 )	2 years ago
Daniel Hiltgen	ceea599494	Merge pull request #2150 from dhiltgen/default_version Set a default version using git describe	2 years ago
Daniel Hiltgen	3005ec74b3	Set a default version using git describe If a VERSION is not specified, this will generate a version string that represents the state of the repo. For example `0.1.21-12-gffaf52e-dirty` representing 12 commits away from 0.1.21 tag, on commit gffaf52e and the tree is dirty.	2 years ago
Daniel Hiltgen	0759d8996e	Merge pull request #2148 from dhiltgen/intel_mac Refine Accelerate usage on mac	2 years ago
Daniel Hiltgen	0f5b843319	Refine Accelerate usage on mac For old macs, accelerate seems to cause crashes, but for AVX2 capable macs, it does not.	2 years ago
Jeffrey Morgan	ffaf52e1e9	update submodule to `011e8ec577fd135cbc02993d3ea9840c516d6a1c`	2 years ago
Michael Yang	940b10b036	Merge pull request #2144 from jmorganca/mxyng/update-faq faq: update to use launchctl setenv	2 years ago
Daniel Hiltgen	3bc28736cd	Merge pull request #2143 from dhiltgen/llm_verbosity Refine debug logging for llm	2 years ago
Michael Yang	93a756266c	faq: update to use launchctl setenv	2 years ago
Daniel Hiltgen	a0a829bf7a	Merge pull request #2142 from dhiltgen/debug_on_fail Debug logging on init failure	2 years ago
Daniel Hiltgen	730dcfcc7a	Refine debug logging for llm This wires up logging in llama.cpp to always go to stderr, and also turns up logging if OLLAMA_DEBUG is set.	2 years ago
Daniel Hiltgen	27a2d5af54	Debug logging on init failure	2 years ago
Jeffrey Morgan	5f81a33f43	update submodule to `6f9939d` (#2115 )	2 years ago
Michael Yang	6225fde046	Merge pull request #2102 from jmorganca/mxyng/fix-create-override fix: remove overwritten model layers	2 years ago
Meng Zhuo	069184562b	readline: drop not use min function (#2134 )	2 years ago
Daniel Hiltgen	5576bb2348	Merge pull request #2130 from dhiltgen/more_faster Make CPU builds parallel and customizable AMD GPUs	2 years ago
Daniel Hiltgen	2738837786	Merge pull request #2131 from dhiltgen/probe_cards_at_init Probe GPUs before backend init	2 years ago
Daniel Hiltgen	ec3764538d	Probe GPUs before backend init Detect potential error scenarios so we can fallback to CPU mode without hitting asserts.	2 years ago
Daniel Hiltgen	df54c723ae	Make CPU builds parallel and customizable AMD GPUs The linux build now support parallel CPU builds to speed things up. This also exposes AMD GPU targets as an optional setting for advaced users who want to alter our default set.	2 years ago
Daniel Hiltgen	fa8c990e58	Merge pull request #2127 from dhiltgen/rocm_container Combine the 2 Dockerfiles and add ROCm	2 years ago
Daniel Hiltgen	da72235ebf	Combine the 2 Dockerfiles and add ROCm This renames Dockerfile.build to Dockerfile, and adds some new stages to support 2 modes of building - the build_linux.sh script uses intermediate stages to extract the artifacts for ./dist, and the default build generates a container image usable by both cuda and rocm cards. This required transitioniing the x86 base to the rocm image to avoid layer bloat.	2 years ago
Jeffrey Morgan	89c4aee29e	Unlock mutex when failing to load model (#2117 )	2 years ago
Jeffrey Morgan	f32ea81b21	increase minimum overhead to 1024MiB (#2114 )	2 years ago
Jeffrey Morgan	4c54f0ddeb	sign dylibs on macOS (#2101 )	2 years ago
Michael Yang	c08dfaa23d	fix: remove overwritten model layers if create overrides a manifest, first add the older manifest's layers to the delete map so they can be cleaned up	2 years ago
Daniel Hiltgen	3b76e736ae	Merge pull request #2100 from dhiltgen/more_wsl_globs More WSL paths	2 years ago
Daniel Hiltgen	552db98bf1	More WSL paths	2 years ago
Daniel Hiltgen	fdcdfef620	Merge pull request #2099 from dhiltgen/fix_cuda_model_swap Switch to local dlopen symbols	2 years ago
Daniel Hiltgen	6a042438af	Switch to local dlopen symbols	2 years ago
Jeffrey Morgan	dc88cc3981	use `gzip` for runner embedding (#2067 )	2 years ago
Daniel Hiltgen	62976087c6	Merge pull request #1999 from lainedfles/termux_android_cpu_only Fix CPU-only build under Android Termux enviornment.	2 years ago
Self Denial	344342abdf	Restore dyn_ext_server.c since RTLD_DEEPBIND has been removed	2 years ago
Self Denial	eb76f3e379	Fix CPU-only build under Android Termux enviornment. Update gpu.go initGPUHandles() to declare gpuHandles variable before reading it. This resolves an "invalid memory address or nil pointer dereference" error. Update dyn_ext_server.c to avoid setting the RTLD_DEEPBIND flag under __TERMUX__ (Android).	2 years ago
Michael Yang	d017e3d0a6	Merge pull request #2060 from jmorganca/mxyng/fix-show fix show handler	2 years ago
Michael Yang	aac9ab4db7	fix show handler	2 years ago
Michael Yang	1f5b7ff976	Merge pull request #1932 from jmorganca/mxyng/api-fields api: add model for all requests	2 years ago
Michael Yang	e299831e2c	Merge pull request #1958 from purificant/ci ci: update setup-go action	2 years ago
Michael Yang	745b5934fa	add model to ModelResponse	2 years ago
Michael Yang	a38d88d828	api: add model for all requests prefer using req.Model and fallback to req.Name	2 years ago
Daniel Hiltgen	abec7f06e5	Merge pull request #2056 from dhiltgen/slog Mechanical switch from log to slog	2 years ago
Michael Yang	e5da190bac	Merge pull request #2020 from jmorganca/mxyng/install-fedora install: pin fedora to max 37	2 years ago
Daniel Hiltgen	ecbfc0182f	Go bump to v1.21 to pick up slog	2 years ago
Daniel Hiltgen	fedd705aea	Mechanical switch from log to slog A few obvious levels were adjusted, but generally everything mapped to "info" level.	2 years ago
Mike Bird	82ee019bfc	add open interpreter to list of extensions (#2016 )	2 years ago
Sachin Sachdeva	ad9dbc2a04	Haystack Ollama Integration (#2021 ) Updated readme with the web link for haystack ollama integration	2 years ago
Daniel Hiltgen	fccdf4c635	Merge pull request #1987 from xyproto/archlinux Let gpu.go and gen_linux.sh also find CUDA on Arch Linux	2 years ago
Daniel Hiltgen	d450fb1d1e	Merge pull request #2055 from dhiltgen/cuda_docs Refine the linux cuda/rocm developer docs	2 years ago
Daniel Hiltgen	df40b11d03	Merge pull request #2007 from dhiltgen/cpu_fallback Add multiple CPU variants for Intel Mac	2 years ago
Daniel Hiltgen	9cd20b0ec8	Refine the linux cuda/rocm developer docs	2 years ago
Daniel Hiltgen	b992bf65fc	Disable arm64 for test phase The runners are x86 so we can only run binaries that match.	2 years ago

1 2 3 4 5 ...

1863 Commits (4458efb73afe76ead7e0ec3e088564fb3aea1900) All Branches Search

1863 Commits (4458efb73afe76ead7e0ec3e088564fb3aea1900)

All Branches