Fix per-layer quant dtype in DeepSeek R1 attention init#1
Closed
thpereir wants to merge 1 commit intothpereir/quark_quant_layerfrom
Closed
Fix per-layer quant dtype in DeepSeek R1 attention init#1thpereir wants to merge 1 commit intothpereir/quark_quant_layerfrom
thpereir wants to merge 1 commit intothpereir/quark_quant_layerfrom
Conversation
For mixed-precision models (e.g. MXFP4 MoE + FP8 attention), the attention block must resolve its own per-layer quant spec rather than using the global quant_config['quant_dtype']. - Add _attn_spec / _attn_quant_dtype via quant_config.resolve(prefix) - Use resolved dtype for FP4/FP8 decision in attention init - Pass prefix to MergedReplicatedLinear for fused_qkv_a_proj - Use resolved dtype for fuse_qknorm_quant decision Tested with DeepSeek-R1-0528-moe-mxfp4-other-ptpc on TP=4.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
For mixed-precision models (e.g. MXFP4 MoE + FP8 attention), the attention block must resolve its own per-layer quant spec rather than using the global quant_config['quant_dtype'].
Tested with DeepSeek-R1-0528-moe-mxfp4-other-ptpc on TP=4.
Depends on ROCm#236