This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
78300cdabffbaaffe7625ed34412ec2aec75535c
vLLM
/
vllm
/
models
/
kimi_k3
/
nvidia
/
ops
T
History
Yongye Zhu
and
OpenAI Codex
3ba9907a1d
[Kimi-K3] Overlap low-M TP8 KDA projections (
#54697
)
...
Signed-off-by: Yongye Zhu <
zyy1102000@gmail.com
> Co-authored-by: OpenAI Codex <
codex@openai.com
>
2026-09-02 03:35:28 +00:00
..
cute_dsl
[Kimi-K3] Overlap low-M TP8 KDA projections (
#54697
)
2026-09-02 03:35:28 +00:00
third_party
[Model] Add Kimi K3 support: model files and kernels [1/N] (
#50089
)
2026-07-29 14:10:58 +08:00
__init__.py
…
attn_res.py
[Kimi-K3][Perf] Make native CUDA AttnRes the SM100 default (
#54261
)
2026-08-31 23:18:12 +00:00
fused_mla_key_concat_kv_cache.py
[Attention][MLA] Fuse Kimi-K3 chunked-context K/V packing (
#51772
)
2026-08-12 22:42:57 -07:00
latent_moe_tail.py
[Kimi-K3][Kernel] Optimize the low-M fused latent MoE tail (
#54168
)
2026-08-28 10:45:36 -07:00
recoverssm.py
[K3] support recoverssm for K3 (
#51855
)
2026-08-17 19:34:14 +08:00
vision_fa4_warmup.py
[Model] Add Kimi K3 support: model files and kernels [1/N] (
#50089
)
2026-07-29 14:10:58 +08:00