[Feature][Frontend] Expose effective attention block size for DCP (#56538)
Co-authored-by: Bugen Zhao <i@bugenzhao.com> Co-authored-by: OpenAI Codex <noreply@openai.com> Signed-off-by: Julien Darve <jdarve@NVIDIA.com> Signed-off-by: Bugen Zhao <i@bugenzhao.com>
This commit is contained in:
co-authored by
Bugen Zhao
OpenAI Codex
parent
0d8173d153
commit
f37c550bf6
@@ -215,6 +215,9 @@ def test_cache_config_hash_ignores_kv_cache_sizing_knobs():
|
||||
base_hash = CacheConfig().compute_hash()
|
||||
assert CacheConfig(kv_cache_memory_bytes=1 << 30).compute_hash() == base_hash
|
||||
assert CacheConfig(gpu_memory_utilization=0.5).compute_hash() == base_hash
|
||||
config = CacheConfig()
|
||||
config.effective_attention_block_size = 64
|
||||
assert config.compute_hash() == base_hash
|
||||
|
||||
|
||||
def test_scheduler_config_hash_includes_max_num_seqs():
|
||||
|
||||
Reference in New Issue
Block a user