biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] Pass Renderer to Input Processor (#34329)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-02-12 11:38:11 +08:00
committed by GitHub
parent ced2a92f40
commit b96f7314b4
20 changed files with 107 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/models/language/generation/test_hybrid.py
View File

@@ -507,7 +507,8 @@ def test_apc_single_prompt_block_align_alignment(
vllm_runner_kwargs["enable_prefix_caching"] = True
with vllm_runner(**vllm_runner_kwargs) as vllm_model:
# Retrieve the default mamba state block size
mamba_block_size = vllm_model.llm.llm_engine.cache_config.mamba_block_size
vllm_config = vllm_model.llm.llm_engine.vllm_config
mamba_block_size = vllm_config.cache_config.mamba_block_size
# In case the hybrid model does not have the
# "mamba_block_size" assume a fixed constant
@@ -660,7 +661,8 @@ def test_apc_multiple_prompts_block_align_alignment(
vllm_runner_kwargs["enable_prefix_caching"] = True
with vllm_runner(**vllm_runner_kwargs) as vllm_model:
# Retrieve the default mamba state block size
mamba_block_size = vllm_model.llm.llm_engine.cache_config.mamba_block_size
vllm_config = vllm_model.llm.llm_engine.vllm_config
mamba_block_size = vllm_config.cache_config.mamba_block_size
# In case the hybrid model does not have the
# "mamba_block_size" assume a fixed constant