Add Mixtral-8x7B MoE KV-compression kernel and results#45
Merged
Conversation
Adds K3V2/K4V2 quant-only KV compression coverage for Mixtral-8x7B-Instruct (NF4 weights) on a single T4 via per-layer CPU/GPU streaming. PPL deltas (AQUA-iso paired, n=80): K3V2 +0.63%, K4V2 +0.32% off the NF4-weights baseline. Needle retrieval at 4K context holds at 5/5 for FP16, K3V2, and K4V2. Claude-Session: https://claude.ai/code/session_012T2q1cWGCTY963GGFXRZA7
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds K3V2/K4V2 quant-only KV compression coverage for Mixtral-8x7B-Instruct (NF4 weights) on a single T4 via per-layer CPU/GPU streaming. PPL deltas (AQUA-iso paired, n=80): K3V2 +0.63%, K4V2 +0.32% off the NF4-weights baseline. Needle retrieval at 4K context holds at 5/5 for FP16, K3V2, and K4V2.
Closes the MoE-architecture coverage gap.
https://claude.ai/code/session_012T2q1cWGCTY963GGFXRZA7