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

[Bugfix] Fix 2 precommit issues - (mamba_block_size, kv_cache_config) (#27811)

Browse Source 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
This commit is contained in:
Tyler Michael Smith
2025-10-30 14:52:18 -04:00
committed by GitHub
parent 2918c1b49c
commit ab98f6556f
2 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/config.py
View File

@@ -406,7 +406,7 @@ class HybridAttentionMambaModelConfig(VerifyAndUpdateConfig):
# easily by changing the way we layout chunks in the
# mamba2 kernels.
base_chunk_size = model_config.get_mamba_chunk_size()
base_chunk_size = mamba_block_size or model_config.get_mamba_chunk_size()
attn_tokens_per_mamba_state = cdiv(mamba_page_size, attn_page_size_1_token)
chunk_size = lcm(base_chunk_size, kernel_block_alignment_size)
attn_block_size = chunk_size * cdiv(attn_tokens_per_mamba_state, chunk_size)