MOVZX
76df77c04e
Merge branch 'main' into patches
...
Signed-off-by: MOVZX <movzx@yahoo.com >
2026-10-15 21:16:39 +07:00
Rohan Potdar and Claude Opus 5.5
52a8cc5316
[ROCm][CI] Add dtype to the KDA metadata test's fake model config ( #61650 )
...
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-14 18:04:14 +00:00
Nick Hill
c059bee812
[MRV2] Switch CI tests still running on MRV1 unnecessarily ( #61014 )
...
Signed-off-by: Nick Hill <nickhill123@gmail.com >
2026-10-11 09:57:07 -07:00
MOVZX
ac305c44cb
Merge branch 'main' into patches
...
Signed-off-by: MOVZX <movzx@yahoo.com >
2026-10-09 17:41:13 +00:00
d8fa463e2b
[Bugfix][Prefix caching] Fix inconsistent hybrid Mamba prefix cache boundaries ( #60533 )
...
Signed-off-by: Wei Zhao <weizha@aws-cmh-slurm-1-login-01.cm.cluster >
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: Wei Zhao <weizha@aws-cmh-slurm-1-login-01.cm.cluster >
Co-authored-by: Codex <noreply@openai.com >
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-08 18:33:48 +00:00
0eac152707
[Bugfix] Route every speculation-capable row through the speculative path so recurrent state stays consistent ( #56531 )
...
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com >
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-06 03:03:44 +04:00
MOVZX and Hinata
ae0350c0de
[Spec Decode][MRV2] RecoverSSM for Qwen GDN and PLE short conv (PR #58863 )
...
Intake of open upstream PR vllm-project/vllm#58863 . Active only with
VLLM_USE_V2_MODEL_RUNNER=1; inert otherwise.
Speculative decoding on Gated DeltaNet snapshotted the full recurrent
state after every draft position and reserved one Mamba block per draft
position. On a 24 GB card that is reserved VRAM we never use, plus
per-step copy traffic.
RecoverSSM, the protocol Kimi-K3 KDA already uses, replaces this:
verify runs from a read-only checkpoint and stores a small per-token
replay record [correction (V), normalized key (K), gate (1)] in fp32;
commit replays only the accepted tokens and writes the recurrent state
once, plus the block-boundary state in align mode. The PLE dilated
short conv compacts its accepted window with the same plan.
Conflict in vllm/models/qwen4_exp/nvidia/mtp.py: our get_top_tokens()
work put LocalArgmaxMixin on Qwen4ExpMTP, the PR adds SupportsReplaySSM
to the same base list. Kept both.
Co-Authored-By: Hinata <hinata@idihore.id >
Signed-off-by: MOVZX <movzx@yahoo.com >
2026-09-29 13:39:09 +07:00
dd3bc9c72f
[Perf][MRV2] Reuse Mamba/GDN metadata across KV cache groups ( #58762 )
...
Signed-off-by: Luca Motz <luca.motz@icloud.com >
Co-authored-by: Xin Yang <xyangx@amazon.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Co-authored-by: Codex <noreply@openai.com >
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com >
2026-09-28 04:36:58 +00:00
Jürgen Schmied and Claude
a80e41d690
[Mamba] Share RecoverSSM commit kernels and helpers across models
...
RecoverSSM's commit-plan and conv-window compaction kernels are model independent.
Move them from models/kimi_k3 into model_executor/layers/mamba/ops/recoverssm.py
(Kimi-K3 keeps its private names as import aliases; kernel source unchanged), add
mamba/recoverssm_utils.py (activation predicate, argument validation) and the
generic spec-row/request mapping helpers to v1/attention/backends/recoverssm_metadata.py.
CacheConfig.use_kda_recoverssm becomes use_recoverssm: the switch now selects RecoverSSM
for any model whose recurrent layers implement it, not only KDA.
No functional change for Kimi-K3.
Signed-off-by: Jürgen Schmied <juergenschmied70@gmail.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-09-27 00:07:04 +02:00
1417022c3d
[ROCm][Kimi-K3] Optimize low-concurrency speculative KDA ( #58045 )
...
Signed-off-by: jiacao-amd <jiahui.cao@amd.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-09-25 12:33:30 -05:00
Harry Mellor and Claude Opus 5
651a88c09a
[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings ( #57212 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
2026-09-16 10:57:24 -07:00
Harry Mellor and Claude Opus 5
8c1557a79c
Add pydocstyle to the ruff rules ( #52136 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Signed-off-by: Harry Mellor <hej.mellor@gmail.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
2026-09-16 16:44:29 +00:00
sashko-zakharchuk and zjy0516
f8b5c11468
[Bugfix][Kimi-K3] Do not classify a stateless first chunk as a decode ( #51483 )
...
Signed-off-by: Oleksandr Zakharchuk <oleksandr.zakharchuk@gmail.com >
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com >
2026-09-16 21:24:48 +08:00
Wentao Ye
86aca66191
[Kimi K3 Perf] Avoid KDA mixed-batch gather/scatter, 5.2%~7.7% E2E Throughput Improvement ( #56159 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-09-10 17:57:01 +08:00
Wei Zhao
a69402aaa8
[Perf] Integrate FlashInfer KDA kernels ( #55364 )
...
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com >
2026-09-07 20:29:30 -07:00
Ziming Huang and OpenAI Codex
144e79c810
[Kimi K3] Support internal prefix checkpoints with partial prefix caching and spec-decoding ( #53614 )
...
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-09-06 13:18:15 +08:00
6cbb3c154e
[Perf][GDN] Build cudagraph-capture metadata without a device sync ( #55404 )
...
Signed-off-by: Nick Hill <nickhill123@gmail.com >
Co-authored-by: Roger Wang <rogerw@inferact.ai >
Co-authored-by: Kimi Code <noreply@moonshot.cn >
2026-09-04 17:40:17 -07:00
Wentao Ye
fc72fc39ac
[Kimi Bug] Fix cannot access local variable 'active_non_spec_mask_cpu' ( #54781 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-09-01 21:08:50 +00:00
Wentao Ye
0e30bd62fe
[CI Bug] Fix kimi test AssertionError: Aligned Mamba state indices must be precomputed ( #53766 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-08-25 15:06:14 -04:00
Wentao Ye
41729fc53b
[K3 Perf] Optimize k3 mamba metadata preparation, 6.6~7.6x kernel performance improvement ( #52388 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-08-25 11:00:28 -04:00
9eb9d9d395
[Perf] Support internal prefill checkpoints for Mamba prefix caching, 9%~25% TTFT improvement ( #52789 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com >
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
Co-authored-by: Ziming Huang <zelda.huanghuang@gmail.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-08-22 10:32:40 -07:00
70afdedc10
[K3] support recoverssm for K3 ( #51855 )
...
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com >
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-17 19:34:14 +08:00
+12
7c6729b769
[Model] Add Kimi K3 support: model files and kernels [1/N] ( #50089 )
...
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: Yongye Zhu <zyy1102000@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 >
2026-07-29 14:10:58 +08:00