[New model] Kimi K3 (#50000)

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Ziming Huang <zelda.huanghuang@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Summer Yang <girasoleyang@gmail.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: gnovack <novackgm@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: xiaozhoupy <peiyuanzhou1994@gmail.com>
Co-authored-by: Roy Wang <yasong.wang@inferact.ai>
Co-authored-by: Jeff (Junze) Ma <93145857+majunze2001@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
This commit is contained in:
Jiangyun Zhu
2026-07-30 03:49:58 -07:00
committed by GitHub
co-authored by Isotr0py Thien Tran Bugen Zhao Yongye Zhu Ziming Huang Roger Wang Isotr0py aoshen02 Woosuk Kwon Jee Jee Li aoshen02 Summer Yang Kevin H. Luu Bowen Wang gnovack Nick Hill Yifan Qiao xiaozhoupy Roy Wang Jeff Ma Codex Wei Zhao
parent 0c64be8873
commit aeeb36b1f1
82 changed files with 2927 additions and 1345 deletions
+13 -1
View File
@@ -385,6 +385,8 @@ class MLAAttentionSpec(FullAttentionSpec):
alignment: int | None = None # Default to None for no padding.
compress_ratio: int = 1 # Default to 1 for no compression.
model_version: str | None = None
# Marks draft groups that flatten a non-causal query block into decode rows.
non_causal_multi_token_decode: bool = False
def __post_init__(self):
super().__post_init__()
@@ -434,7 +436,7 @@ class MLAAttentionSpec(FullAttentionSpec):
"quantization method, compress ratio, model version, and KV block "
"stride indexing."
)
return cls(
merged_spec = cls(
block_size=specs[0].block_size,
num_kv_heads=specs[0].num_kv_heads,
head_size=specs[0].head_size,
@@ -445,7 +447,17 @@ class MLAAttentionSpec(FullAttentionSpec):
cache_dtype_str=cache_dtype_str_set.pop(),
compress_ratio=compress_ratio_set.pop(),
model_version=model_version_set.pop(),
non_causal_multi_token_decode=any(
spec.non_causal_multi_token_decode for spec in specs
),
)
for spec in specs:
for f in fields(AttentionSpec):
assert getattr(spec, f.name) == getattr(merged_spec, f.name), (
"All attention layers in the same KV cache group must have "
"the same attention spec."
)
return merged_spec
@dataclass(frozen=True, kw_only=True)