Open
Conversation
|
Thanks for your contribution! |
|
|
lizexu123
reviewed
Mar 20, 2026
| 4 if not self.speculative_decoding else (self.speculative_config.num_speculative_tokens + 1) * 4 | ||
| ) | ||
| self.infer_seed_increment = paddle.full( | ||
| shape=[self.scheduler_config.max_num_seqs, 1], fill_value=self.increment_value, dtype="int64" |
| return scale.max(axis=1).values.cast("float32") | ||
| raise ValueError(f"{name} rank not supported: shape={scale.shape}") | ||
|
|
||
| w1_alpha = _to_expert_scale_vec(layer.g1_alphas, "g1_alphas") |
Collaborator
There was a problem hiding this comment.
这边改成flashinfer_cutedsl_moe.py的接口
| gate: nn.Layer, | ||
| topk_ids_hookfunc: Callable = None, | ||
| ) -> paddle.Tensor: | ||
| pass |
Collaborator
There was a problem hiding this comment.
这里把flashinfer_cutlass的补全，它只能跑prefill
| def load_up_proj_weight_first(self) -> bool: | ||
| # FlashInfer CUTLASS kernel assumes [Up, Gate] Proj as W13 | ||
| # 目前默认给True | ||
| return False |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Modifications
Usage or Command
Accuracy Tests
Checklist
[FDConfig],[APIServer],[Engine],[Scheduler],[PD Disaggregation],[Executor],[Graph Optimization],[Speculative Decoding],[RL],[Models],[Quantization],[Loader],[OP],[KVCache],[DataProcessor],[BugFix],[Docs],[CI],[Optimization],[Feature],[Benchmark],[Others],[XPU],[HPU],[GCU],[DCU],[Iluvatar],[Metax]]pre-commitbefore commit.releasebranch, make sure the PR has been submitted to thedevelopbranch, then cherry-pick it to thereleasebranch with the[Cherry-Pick]PR tag.