[ROCm][DSv4] Functional fixes for DeepSeek V4 on MI300X/MI325X (#45681)

Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: Markus Hartikainen <markus.hartikainen@amd.com>
Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Co-authored-by: ganyi <ygan@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Markus Hartikainen <markus.hartikainen@amd.com>
Co-authored-by: Jin Tao <jintao12@amd.com>
This commit is contained in:
Tuukka Sarvi
2026-06-18 12:21:14 +00:00
committed by GitHub
co-authored by ganyi Cursor Markus Hartikainen Jin Tao
parent 8d4f54966c
commit afdcbd5d39
8 changed files with 545 additions and 52 deletions
+3 -1
View File
@@ -3,7 +3,9 @@
import torch
import torch.nn as nn
from vllm.models.deepseek_v4.common.ops import fused_inv_rope_fp8_quant
from vllm.models.deepseek_v4.common.ops.fused_inv_rope_fp8_quant import (
fused_inv_rope_fp8_quant,
)
from vllm.platforms import current_platform
from vllm.utils.deep_gemm import fp8_einsum