support Qwen3.5 FP8 Model on GCU (Enflame) - #358
Open
liuyancong-enflame-tech wants to merge 13 commits into
Open
support Qwen3.5 FP8 Model on GCU (Enflame)#358liuyancong-enflame-tech wants to merge 13 commits into
liuyancong-enflame-tech wants to merge 13 commits into
Conversation
Contributor
Author
|
Base PR330 |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| if hasattr(mod, "apply_moe_activation"): | ||
| mod.apply_moe_activation = apply_moe_activation_gcu | ||
|
|
||
| _patched = True |
| from vllm.model_executor.layers.quantization.fp8 import Fp8Config | ||
|
|
||
| Fp8Config.get_min_capability = classmethod(_gcu_get_min_capability) | ||
| _patched = True |
| # mod.moe_align_block_size = moe_align_block_size_gcu | ||
| mod.moe_align_block_size = moe_align_block_size_torch | ||
|
|
||
| _patched = True |
| # TritonWNA16Experts which inherits from TritonExperts) use the | ||
| # GCU-compatible implementation. | ||
| TritonExperts.moe_sum = _gcu_moe_sum_impl | ||
| _patched = True |
| if hasattr(mod, "per_token_group_quant_fp8"): | ||
| mod.per_token_group_quant_fp8 = per_token_group_quant_fp8_gcu | ||
|
|
||
| _patched = True |
Comment on lines
+42
to
+43
| "vllm.model_executor.layers.quantization.compressed_tensors." | ||
| "compressed_tensors_moe.compressed_tensors_moe_w4a8_fp8", |
| # references to the same class object everywhere. | ||
| mod.QuantFP8.forward_oot = mod.QuantFP8.forward_cuda | ||
|
|
||
| _patched = True |
| invoke_fused_moe_triton_kernel_gcu | ||
| ) | ||
|
|
||
| _patched = True |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Category
PR Type
Description
Related Issues
Changes
Testing
Checklist