- 28 Apr, 2025 1 commit
-
-
Devon Rifkin authored
This reverts commit 424f6486.
-
- 22 Apr, 2025 1 commit
-
-
Devon Rifkin authored
* 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`
-
- 27 Mar, 2025 1 commit
-
-
Parth Sareen authored
-
- 13 Mar, 2025 1 commit
-
-
Bradley Erickson authored
-
- 10 Mar, 2025 1 commit
-
-
frob authored
-
- 07 Feb, 2025 2 commits
-
-
Azis Alvriyanto authored
-
Leisure Linux authored
-
- 03 Dec, 2024 1 commit
-
-
Sam authored
-
- 25 Sep, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 18 Sep, 2024 1 commit
-
-
Patrick Devine authored
-
- 10 Sep, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 02 Sep, 2024 1 commit
-
-
SnoopyTlion authored
-
- 23 Aug, 2024 1 commit
-
-
Michael Yang authored
-
- 29 Jul, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 23 Jul, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 10 Jul, 2024 1 commit
-
-
Daniel Hiltgen authored
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.
-
- 02 Jul, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 28 Jun, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 21 May, 2024 1 commit
-
-
Patrick Devine authored
-
- 14 May, 2024 1 commit
-
-
Patrick Devine authored
-
- 06 May, 2024 1 commit
-
-
Jeffrey Chen authored
-
- 05 May, 2024 1 commit
-
-
Daniel Hiltgen authored
This also bumps up the default to be 50 queued requests instead of 10.
-
- 03 May, 2024 1 commit
-
-
Dr Nic Williams authored
* Update 'llama2' -> 'llama3' in most places --------- Co-authored-by:Patrick Devine <patrick@infrahq.com>
-
- 24 Apr, 2024 1 commit
-
-
Patrick Devine authored
-
- 26 Mar, 2024 1 commit
-
-
Patrick Devine authored
-
- 21 Mar, 2024 2 commits
-
-
Daniel Hiltgen authored
-
Bruce MacDonald authored
-
- 20 Mar, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 18 Mar, 2024 2 commits
-
-
Jeffrey Morgan authored
-
jmorganca authored
-
- 12 Mar, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 21 Feb, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 20 Feb, 2024 2 commits
-
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
- 19 Feb, 2024 2 commits
-
-
Patrick Devine authored
-
Daniel Hiltgen authored
-
- 16 Feb, 2024 1 commit
-
-
Tristan Rhodes authored
-
- 22 Jan, 2024 1 commit
-
-
Michael Yang authored
-
- 22 Dec, 2023 2 commits
-
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Matt Williams authored
* 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>
-