[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
+32
View File
@@ -25,6 +25,9 @@ from vllm.model_executor.layers.fused_moe.config import (
FusedMoEQuantDesc,
fp8_w8a8_moe_quant_config,
)
from vllm.model_executor.layers.fused_moe.deep_gemm_utils import (
deepgemm_moe_permute,
)
from vllm.model_executor.layers.fused_moe.experts.triton_deep_gemm_moe import (
TritonOrDeepGemmExperts,
)
@@ -41,6 +44,35 @@ from vllm.utils.deep_gemm import (
BLOCK_SIZE = [128, 128]
@pytest.mark.skipif(not is_deep_gemm_supported(), reason="Requires deep_gemm kernels")
def test_deepgemm_moe_permute_initializes_padding_scales(workspace_init):
hidden_states = torch.randn(2, 128, device="cuda", dtype=torch.bfloat16)
activations, scales = per_token_group_quant_fp8(
hidden_states,
group_size=128,
use_ue8m0=True,
)
topk_ids = torch.tensor([[0], [1]], device="cuda", dtype=torch.int64)
_, permuted_scales, expert_ids, _, _ = deepgemm_moe_permute(
aq=activations,
aq_scale=scales,
topk_ids=topk_ids,
local_num_experts=2,
expert_map=None,
expert_tokens_meta=None,
)
padding = expert_ids < 0
assert padding.any()
torch.testing.assert_close(
permuted_scales[padding],
torch.zeros_like(permuted_scales[padding]),
rtol=0,
atol=0,
)
def make_block_quant_fp8_weights(
e: int,
n: int,