Open
Conversation
|
|
||
| sorted_ids = sorted_token_ids.contiguous() | ||
| sorted_eids = sorted_expert_ids.contiguous() | ||
| sorted_size = int(sorted_ids.numel()) |
Contributor
|
|
||
| sorted_ids = sorted_token_ids.contiguous() | ||
| sorted_eids = sorted_expert_ids.contiguous() | ||
| sorted_size = int(sorted_ids.numel()) |
Contributor
| import aiter | ||
| from aiter import dtypes | ||
| from aiter.test_common import checkAllclose, benchmark, run_perftest | ||
| from aiter.int4_utils import * |
Contributor
| w1_scale_aiter = w1_scale | ||
| w2_scale_aiter = w2_scale | ||
| if WQDType == torch.int4: # int4 w quant | ||
| w1_qt_aiter = rearrange_4bit_elements( |
Contributor
| w2_scale_aiter = w2_scale | ||
| if WQDType == torch.int4: # int4 w quant | ||
| w1_qt_aiter = rearrange_4bit_elements( | ||
| convert_int8_to_uint32_int4( |
Contributor
| shuffle_weight(w1_qt_aiter, (16, 16), use_int4=True) | ||
| ) | ||
| ) | ||
| w2_qt_aiter = rearrange_4bit_elements( |
Contributor
| ) | ||
| ) | ||
| w2_qt_aiter = rearrange_4bit_elements( | ||
| convert_int8_to_uint32_int4( |
Contributor
| sorted_ids = sorted_ids.contiguous() | ||
| sorted_w = sorted_w.contiguous() | ||
| sorted_eids = sorted_eids.contiguous() | ||
| sorted_size = int(sorted_ids.numel()) |
Contributor
| from aiter.fused_moe_bf16_asm import asm_moe | ||
| from aiter.ops.shuffle import shuffle_weight | ||
| from aiter import pertoken_quant | ||
| from aiter.int4_utils import * |
Contributor
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Technical Details
Test Plan
Test Result
Submission Checklist