[New Model][ROCm] Add AMD support for DeepSeek V4 (#40871)

Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Co-authored-by: ganyi <ygan@amd.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
This commit is contained in:
Hexiang Wang
2026-05-05 08:55:37 -07:00
committed by GitHub
co-authored by ganyi tjtanaa tjtanaavllm
parent 2228fe6868
commit 628c436301
22 changed files with 939 additions and 134 deletions
@@ -499,13 +499,31 @@ class SparseAttnIndexer(CustomOp):
k: torch.Tensor,
weights: torch.Tensor,
):
assert not self.skip_k_cache_insert, (
"AMD platform doesn't support skip cache insert yet"
)
assert not self.use_fp4_cache, "AMD platform doesn't support fp4 cache yet"
assert isinstance(q_quant, torch.Tensor), (
"AMD sparse_attn_indexer expects a single FP8 q_quant tensor"
)
if self.skip_k_cache_insert or not rocm_aiter_ops.is_enabled():
from vllm.v1.attention.ops.rocm_aiter_mla_sparse import (
rocm_aiter_sparse_attn_indexer_native,
)
return rocm_aiter_sparse_attn_indexer_native(
hidden_states,
_encode_layer_name(self.k_cache.prefix),
self.k_cache.kv_cache,
q_quant,
k,
weights,
self.quant_block_size,
self.scale_fmt,
self.topk_tokens,
self.head_dim,
self.max_model_len,
self.max_total_seq_len,
self.topk_indices_buffer,
skip_k_cache_insert=self.skip_k_cache_insert,
)
if rocm_aiter_ops.is_enabled():
return torch.ops.vllm.rocm_aiter_sparse_attn_indexer(
hidden_states,
@@ -522,8 +540,4 @@ class SparseAttnIndexer(CustomOp):
self.max_total_seq_len,
self.topk_indices_buffer,
)
else:
raise RuntimeError(
"Sparse attention indexer ROCm custom op requires ROCm "
"Aiter ops to be enabled."
)
raise RuntimeError("Sparse attention indexer ROCm path could not be selected.")