[Feature] Prefill Context Parallel (PCP) basic support (#28718)

Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: FENP <yuanyongjie.yyj@antgroup.com>
Signed-off-by: LookAround <lixushi@huawei.com>
Signed-off-by: Jingchun Gao <gaojingchun1@huawei.com>
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: FENP <yuanyongjie.yyj@antgroup.com>
Co-authored-by: LookAround <lixushi@huawei.com>
Co-authored-by: Jingchun Gao <gaojingchun1@huawei.com>
Co-authored-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: Jingchun Gao <63247409+gjc0824@users.noreply.github.com>
This commit is contained in:
Qiu
2025-11-19 15:52:44 -05:00
committed by GitHub
co-authored by FENP LookAround Jingchun Gao zhenwenqi2024 Jingchun Gao
parent 02f5903b84
commit 2fd893b4ce
27 changed files with 399 additions and 114 deletions
+2 -2
View File
@@ -87,7 +87,7 @@ class InputBatch:
is_spec_decode: bool = False,
is_pooling_model: bool = False,
num_speculative_tokens: int = 0,
dcp_kv_cache_interleave_size: int = 1,
cp_kv_cache_interleave_size: int = 1,
):
self.is_pooling_model = is_pooling_model
self.is_spec_decode = is_spec_decode
@@ -141,7 +141,7 @@ class InputBatch:
block_sizes=block_sizes,
kernel_block_sizes=kernel_block_sizes,
num_speculative_tokens=num_speculative_tokens,
dcp_kv_cache_interleave_size=dcp_kv_cache_interleave_size,
cp_kv_cache_interleave_size=cp_kv_cache_interleave_size,
)
# Sampling-related.