Repository navigation
setup: count the 3-bit models' 262K context against RAM, not a fixed 90 GB - #134
Closed
architectds wants to merge 1 commit into
Closed
architectds wants to merge 1 commit into
architectds wants to merge 1 commit into
Conversation
…ixed 90 GB IQ3_S and IQ3_XXS asked for 262K were cut to 128K on any machine under 90 GB of RAM. The limit is now counted: the experts' arena, plus the context's 8-bit KV (in RAM with KV streaming, ~13.7 KB a token), plus 24 GB of room. - A 64 GB PC still gets 128K for both models, as before. - A box with ~84 GB keeps the 262K it asked for. A Colab A100-40G (83.5 GiB) runs IQ3_S at 262K, with images, in 56 GiB.
Owner
|
Thanks @architectds. Counting what's needed is the right rule, 64 GB PCs keep what they had, and it merges cleanly onto 0.1.26. I'll merge after a quick dry run of the setup paths. |
Owner
|
Released in 0.1.29: the 3-bit models' 262K counted against RAM. Merged under your name (cherry-picked, so GitHub doesn't show it as merged). Thank you! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The second piece from #103, as you suggested.
setup.pycuts IQ3_S and IQ3_XXS asked for 262K down to 128K on any machine under 90 GB of RAM. With KV streaming, the context costs mostly RAM, so this PR counts the need instead: the experts' arena, plus the context's 8-bit KV (~13.7 KB a token, the same figure setup uses for--kv-resident), plus 24 GB of room for everything else.Measured: a Colab A100-40G (83.5 GiB of RAM) runs IQ3_S at 262K with images in 56 GiB.
The check still only applies above 128K, and it still uses the 8-bit KV figure, because the KV precision is asked after the context. Nothing else changes.