Commit graph

88 commits

Author SHA1 Message Date
Daniel Hiltgen
6c2eb73a70
Fix missing dep path on windows CPU runners (#6884)
GPUs handled the dependency path properly, but CPU runners didn't which
results in missing vc redist libraries on systems where the user didn't
already have it installed from some other app.
2024-09-21 16:28:29 -07:00
Daniel Hiltgen
cd5c8f6471
Optimize container images for startup (#6547)
* Optimize container images for startup

This change adjusts how to handle runner payloads to support
container builds where we keep them extracted in the filesystem.
This makes it easier to optimize the cpu/cuda vs cpu/rocm images for
size, and should result in faster startup times for container images.

* Refactor payload logic and add buildx support for faster builds

* Move payloads around

* Review comments

* Converge to buildx based helper scripts

* Use docker buildx action for release
2024-09-12 12:10:30 -07:00
Daniel Hiltgen
93ea9240ae
Move ollama executable out of bin dir (#6535) 2024-08-27 16:19:00 -07:00
Daniel Hiltgen
7a1e1c1caf
gpu: Ensure driver version set before variant (#6480)
During rebasing, the ordering was inverted causing the cuda version
selection logic to break, with driver version being evaluated as zero
incorrectly causing a downgrade to v11.
2024-08-23 11:21:12 -07:00
Daniel Hiltgen
f9e31da946 Review comments 2024-08-19 10:36:15 -07:00
Daniel Hiltgen
88bb9e3328 Adjust layout to bin+lib/ollama 2024-08-19 09:38:53 -07:00
Daniel Hiltgen
4fe3a556fa Add cuda v12 variant and selection logic
Based on compute capability and driver version, pick
v12 or v11 cuda variants.
2024-08-19 09:38:53 -07:00
Daniel Hiltgen
d470ebe78b Add Jetson cuda variants for arm
This adds new variants for arm64 specific to Jetson platforms
2024-08-19 09:38:53 -07:00
Daniel Hiltgen
74d45f0102 Refactor linux packaging
This adjusts linux to follow a similar model to windows with a discrete archive
(zip/tgz) to cary the primary executable, and dependent libraries. Runners are
still carried as payloads inside the main binary

Darwin retain the payload model where the go binary is fully self contained.
2024-08-19 09:38:53 -07:00
Daniel Hiltgen
5bca2e60a7 Harden intel boostrap for nil pointers 2024-08-09 11:31:38 -07:00
Michael Yang
b732beba6a lint 2024-08-01 17:06:06 -07:00
Michael Yang
e2c3f6b3e2 string 2024-07-22 11:27:52 -07:00
Michael Yang
55cd3ddcca bool 2024-07-22 11:27:21 -07:00
Michael Yang
35b89b2eab rfc: dynamic environ lookup 2024-07-22 11:25:30 -07:00
Jeffrey Morgan
c4cf8ad559
llm: avoid loading model if system memory is too small (#5637)
* llm: avoid loading model if system memory is too small

* update log

* Instrument swap free space

On linux and windows, expose how much swap space is available
so we can take that into consideration when scheduling models

* use `systemSwapFreeMemory` in check

---------

Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2024-07-11 16:42:57 -07:00
Daniel Hiltgen
f6f759fc5f Detect CUDA OS Overhead
This adds logic to detect skew between the driver and
management library which can be attributed to OS overhead
and records that so we can adjust subsequent management
library free VRAM updates and avoid OOM scenarios.
2024-07-09 12:21:50 -07:00
Daniel Hiltgen
ef757da2c9 Better nvidia GPU discovery logging
Refine the way we log GPU discovery to improve the non-debug
output, and report more actionable log messages when possible
to help users troubleshoot on their own.
2024-07-03 10:50:40 -07:00
Daniel Hiltgen
b2799f111b Move libraries out of users path
We update the PATH on windows to get the CLI mapped, but this has
an unintended side effect of causing other apps that may use our bundled
DLLs to get terminated when we upgrade.
2024-06-17 13:12:18 -07:00
Jeffrey Morgan
163cd3e77c
gpu: add env var for detecting Intel oneapi gpus (#5076)
* gpu: add env var for detecting intel oneapi gpus

* fix build error
2024-06-16 20:09:05 -04:00
Daniel Hiltgen
6f351bf586 review comments and coverage 2024-06-14 14:55:50 -07:00
Daniel Hiltgen
fc37c192ae Refine CPU load behavior with system memory visibility 2024-06-14 14:51:40 -07:00
Daniel Hiltgen
434dfe30c5 Reintroduce nvidia nvml library for windows
This library will give us the most reliable free VRAM reporting on windows
to enable concurrent model scheduling.
2024-06-14 14:51:40 -07:00
Daniel Hiltgen
4e2b7e181d Refactor intel gpu discovery 2024-06-14 14:51:40 -07:00
Daniel Hiltgen
6fd04ca922 Improve multi-gpu handling at the limit
Still not complete, needs some refinement to our prediction to understand the
discrete GPUs available space so we can see how many layers fit in each one
since we can't split one layer across multiple GPUs we can't treat free space
as one logical block
2024-06-14 14:51:40 -07:00
Daniel Hiltgen
43ed358f9a Refine GPU discovery to bootstrap once
Now that we call the GPU discovery routines many times to
update memory, this splits initial discovery from free memory
updating.
2024-06-14 14:51:40 -07:00
Daniel Hiltgen
efac488675 Revert "Limit GPU lib search for now (#4777)"
This reverts commit 476fb8e892.
2024-06-14 14:51:40 -07:00
Daniel Hiltgen
aac367636d Actually skip PhysX on windows 2024-06-13 13:17:19 -07:00
Michael Yang
bf7edb0d5d lint linux 2024-06-04 11:13:30 -07:00
Jeffrey Morgan
476fb8e892
Limit GPU lib search for now (#4777)
* fix oneapi errors on windows 10
2024-06-01 19:24:33 -07:00
Daniel Hiltgen
646371f56d
Merge pull request #3278 from zhewang1-intc/rebase_ollama_main
Enabling ollama to run on Intel GPUs with SYCL backend
2024-05-28 16:30:50 -07:00
Patrick Devine
4cc3be3035
Move envconfig and consolidate env vars (#4608) 2024-05-24 14:57:15 -07:00
Wang,Zhe
fd5971be0b support ollama run on Intel GPUs 2024-05-24 11:18:27 +08:00
Daniel Hiltgen
30a7d7096c Bump VRAM buffer back up
Under stress scenarios we're seeing OOMs so this should help stabilize
the allocations under heavy concurrency stress.
2024-05-10 09:15:28 -07:00
Daniel Hiltgen
8727a9c140 Record more GPU information
This cleans up the logging for GPU discovery a bit, and can
serve as a foundation to report GPU information in a future UX.
2024-05-09 14:18:14 -07:00
Michael Yang
4736391bfb llm: add minimum based on layer size 2024-05-06 17:04:19 -07:00
Daniel Hiltgen
380378cc80 Use our libraries first
Trying to live off the land for cuda libraries was not the right strategy.  We need to use the version we compiled against to ensure things work properly
2024-05-06 14:23:29 -07:00
Daniel Hiltgen
af9eb36f9f
Merge pull request #4135 from dhiltgen/no_physx
Skip PhysX cudart library
2024-05-06 13:34:00 -07:00
Daniel Hiltgen
06093fd396
Merge pull request #4067 from dhiltgen/cudart
Add CUDA Driver API for GPU discovery
2024-05-06 13:30:27 -07:00
Daniel Hiltgen
f56aa20014 Centralize server config handling
This moves all the env var reading into one central module
and logs the loaded config once at startup which should
help in troubleshooting user server logs
2024-05-05 16:49:50 -07:00
Daniel Hiltgen
b1ad3a43cb Skip PhysX cudart library
For some reason this library gives incorrect GPU information, so skip it
2024-05-03 11:55:32 -07:00
Daniel Hiltgen
089daaeabc Add CUDA Driver API for GPU discovery
We're seeing some corner cases with cudart which might be resolved by
switching to the driver API which comes bundled with the driver package
2024-04-30 18:00:45 -07:00
Daniel Hiltgen
34b9db5afc Request and model concurrency
This change adds support for multiple concurrent requests, as well as
loading multiple models by spawning multiple runners. The default
settings are currently set at 1 concurrent request per model and only 1
loaded model at a time, but these can be adjusted by setting
OLLAMA_NUM_PARALLEL and OLLAMA_MAX_LOADED_MODELS.
2024-04-22 19:29:12 -07:00
Michael Yang
7e33a017c0 partial offloading 2024-04-10 11:37:20 -07:00
Daniel Hiltgen
1f11b52511 Refined min memory from testing 2024-04-01 16:48:33 -07:00
Daniel Hiltgen
526d4eb204 Release gpu discovery library after use
Leaving the cudart library loaded kept ~30m of memory
pinned in the GPU in the main process.  This change ensures
we don't hold GPU resources when idle.
2024-04-01 16:48:33 -07:00
Michael Yang
91b3e4d282 update memory calcualtions
count each layer independently when deciding gpu offloading
2024-04-01 13:16:32 -07:00
Jeremy
dfc6721b20 add support for libcudart.so for CUDA devices (adds Jetson support) 2024-03-25 11:07:44 -04:00
Daniel Hiltgen
6c5ccb11f9 Revamp ROCm support
This refines where we extract the LLM libraries to by adding a new
OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already
idempotenent, so this should speed up startups after the first time a
new release is deployed.  It also cleans up after itself.

We now build only a single ROCm version (latest major) on both windows
and linux.  Given the large size of ROCms tensor files, we split the
dependency out.  It's bundled into the installer on windows, and a
separate download on windows.  The linux install script is now smart and
detects the presence of AMD GPUs and looks to see if rocm v6 is already
present, and if not, then downloads our dependency tar file.

For Linux discovery, we now use sysfs and check each GPU against what
ROCm supports so we can degrade to CPU gracefully instead of having
llama.cpp+rocm assert/crash on us.  For Windows, we now use go's windows
dynamic library loading logic to access the amdhip64.dll APIs to query
the GPU information.
2024-03-07 10:36:50 -08:00
Daniel Hiltgen
be330174dd Allow setting max vram for workarounds
Until we get all the memory calculations correct, this can provide
and escape valve for users to workaround out of memory crashes.
2024-03-06 17:15:06 -08:00
Daniel Hiltgen
9754c6d9d8 Harden AMD driver lookup logic
It looks like the version file doesnt exist on older(?) drivers
2024-02-16 16:20:16 -08:00