Add FP8 KV Cache quant example #113
Merged
Conversation
This file contains 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
kylesayrs
pushed a commit
that referenced
this pull request
Aug 28, 2024
* Add example for quantization kv cache to fp8 * Add eval
markmc
pushed a commit
to markmc/llm-compressor
that referenced
this pull request
Nov 13, 2024
* compute zp, scale if weight exists in module * WIP, gets through 1 forward pass * fix for zeroed out scales * fix model load * style * offload helper fns * pass tests * add test to check that observers are used to populate zp and scale in initialization * fix no calibration case * clean up for PR * fix test * update dependencies * fix forward bug * don't calibrate on weights * dont calib weight in forward * fix zp load * check calibration --------- Co-authored-by: George Ohashi <george@neuralmagic.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
FIX #111