EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Revert "[Refactor] Unify full-graph parameter update logic (#6041)" (#6227)

Browse Source 
This reverts commit 8966a99710.

It breaks the test
`tests/e2e/singlecard/spec_decode/test_mtp_eagle_correctness.py::test_deepseek_mtp_correctness[True-FULL_DECODE_ONLY-2-wemaster/deepseek_mtp_main_random_bf16]`

- vLLM version: v0.14.0
- vLLM main:
d68209402d
This commit is contained in:
wangxiyuan
2026-01-25 15:25:38 +08:00
committed by GitHub
parent 7799c4ca3b
commit 95649344aa
10 changed files with 415 additions and 420 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
vllm_ascend/spec_decode/eagle_proposer.py
View File

@@ -36,7 +36,10 @@ from vllm_ascend.attention.attention_mask import AttentionMaskBuilder
from vllm_ascend.attention.attention_v1 import AscendAttentionState
from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
from vllm_ascend.compilation.acl_graph import (ACLGraphWrapper,
update_full_graph_params)
update_attn_dcp_pcp_params,
update_attn_params,
update_mla_attn_dcp_pcp_params,
update_mla_attn_params)
from vllm_ascend.ops.rotary_embedding import update_cos_sin
from vllm_ascend.ops.triton.spec_decode.utils import \
prepare_inputs_padded_kernel
@@ -1178,9 +1181,21 @@ class EagleProposer(VllmEagleProposer):
# update full-graph params for one spec token
def _update_full_graph_params(self, forward_context, num_tokens, draft_attn_metadatas=None):
update_full_graph_params(
self.runner.attn_backend, self.update_stream, forward_context, num_tokens,
self.vllm_config, self.vllm_config.speculative_config)
if self.vllm_config.model_config.use_mla:
if self.pcp_size * self.dcp_size > 1:
update_mla_attn_dcp_pcp_params(self.update_stream,
forward_context, num_tokens)
else:
update_mla_attn_params(self.update_stream, forward_context,
num_tokens,
self.vllm_config.speculative_config)
else:
if self.pcp_size * self.dcp_size > 1:
update_attn_dcp_pcp_params(self.update_stream, forward_context,
num_tokens)
else:
update_attn_params(self.update_stream, forward_context,
num_tokens, self.vllm_config, draft_attn_metadatas)
# padding tensor into desired size
def _pad_tensor(self, tensor, pad_size):