The current scheduler algorithm of picking the paralellism based on available
VRAM complicates the upcoming dynamic layer memory allocation algorithm. This
changes the default to 1, with the intent going forward that parallelism is
explicit and will no longer be dynamically determined. Removal of the dynamic
logic will come in a follow up.
* increase default context length to 4096
We lower the default numParallel from 4 to 2 and use these "savings" to
double the default context length from 2048 to 4096.
We're memory neutral in cases when we previously would've used
numParallel == 4, but we add the following mitigation to handle some
cases where we would have previously fallen back to 1x2048 due to low
VRAM: we decide between 2048 and 4096 using a runtime check, choosing
2048 if we're on a one GPU system with total VRAM of <= 4 GB. We
purposefully don't check the available VRAM because we don't want the
context window size to change unexpectedly based on the available VRAM.
We plan on making the default even larger, but this is a relatively
low-risk change we can make to quickly double it.
* fix tests
add an explicit context length so they don't get truncated. The code
that converts -1 from being a signal for doing a runtime check isn't
running as part of these tests.
* tweak small gpu message
* clarify context length default
also make it actually show up in `ollama serve --help`
This also adjusts our algorithm to favor our bundled ROCm.
I've confirmed VRAM reporting still doesn't work properly so we
can't yet enable concurrency by default.
* Clean up documentation
Will probably need to update with PRs for new release.
Signed-off-by: Matt Williams <m@technovangelist.com>
* Correcting to fit in 0.1.15 changes
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* addressing comments
Signed-off-by: Matt Williams <m@technovangelist.com>
* more api cleanup
Signed-off-by: Matt Williams <m@technovangelist.com>
* its llava not llama
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Updated hosting to server and documented all env vars
Signed-off-by: Matt Williams <m@technovangelist.com>
* remove last of the cli descriptions
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* update further per conversation with jeff earlier today
Signed-off-by: Matt Williams <m@technovangelist.com>
* cleanup the doc readme
Signed-off-by: Matt Williams <m@technovangelist.com>
* move upgrade to faq
Signed-off-by: Matt Williams <m@technovangelist.com>
* first change
Signed-off-by: Matt Williams <m@technovangelist.com>
* updated
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/faq.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* examples in parent
Signed-off-by: Matt Williams <m@technovangelist.com>
* add exapmle for create model.
Signed-off-by: Matt Williams <m@technovangelist.com>
* update faq
Signed-off-by: Matt Williams <m@technovangelist.com>
* update create model api
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/faq.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* update the readme in docs
Signed-off-by: Matt Williams <m@technovangelist.com>
* update a few more things
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/faq.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/modelfile.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
---------
Signed-off-by: Matt Williams <m@technovangelist.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
Patrick Devine
Daniel Hiltgen
Devon Rifkin
Parth Sareen
Bradley Erickson
frob
Azis Alvriyanto
Leisure Linux
Sam
Jeffrey Morgan
SnoopyTlion
Michael Yang
Daniel Hiltgen
Patrick Devine
Jeffrey Chen
Dr Nic Williams
Bruce MacDonald
Tristan Rhodes
Matt Williams
James Radtke
ToasterUwU
ftorto