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

[feature] support pcp + mtp in full graph (#4572)

Browse Source 
1. support pcp + mtp in full graph
2. pcp/dcp related mtp bugfix
3. support pcp + mtpx

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: zhangsicheng5 <zhangsicheng5@huawei.com>
This commit is contained in:
zhangsicheng5
2025-12-22 16:13:39 +08:00
committed by GitHub
parent 12d581605b
commit 78aa7f2693
10 changed files with 478 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/worker/block_table.py
View File

@@ -75,7 +75,7 @@ class BlockTable:
logical_table_size = max_num_blocks_per_req
duplicate_size = 1
if self.pcp_world_size > 1:
if self.pcp_world_size * self.dcp_world_size > 1:
duplicate_size += num_speculative_tokens
self.block_table = self._make_buffer(max_num_reqs * duplicate_size,
logical_table_size,