|
d229952e25
|
[Fix] Preserve model runner contracts in prefill CUDA graphs (#35452)
Co-authored-by: Oasis-Git <ayw.sirius19@gmail.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
|
2026-09-20 13:53:14 -07:00 |
|
|
|
4793f56835
|
[HiCache] Keep hybrid transfer layer maps stage-local under PP (#39699)
Co-authored-by: Aurick Qiao <6137920+aurickq@users.noreply.github.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
|
2026-09-17 10:18:44 +08:00 |
|
|
Aurick QiaoandAurick Qiao
|
7b7620774c
|
Fix device context during NIXL backend initialization (#38774)
Co-authored-by: Aurick Qiao <6137920+aurickq@users.noreply.github.com>
|
2026-09-16 17:59:24 +08:00 |
|
|
Aurick QiaoandAurick Qiao
|
5dde6e8f02
|
Fix MegaMoE buffer allocation and caching for effective SM budgets (#39223)
Co-authored-by: Aurick Qiao <6137920+aurickq@users.noreply.github.com>
|
2026-09-15 10:24:02 +08:00 |
|
|
Aurick QiaoandAurick Qiao
|
2123aca87e
|
[Fix] Wait for PDL before reading DeepSeek V4 K cache locations (#38409)
Co-authored-by: Aurick Qiao <6137920+aurickq@users.noreply.github.com>
|
2026-09-14 21:04:28 +08:00 |
|
|
Aurick Qiao
|
c389dd0863
|
Fix RunAI object-storage checkpoint index filtering (#38988)
|
2026-09-12 12:25:57 +08:00 |
|
|
Aurick Qiao
|
8392c36bce
|
[Bugfix][Mamba] Clear deferred init metadata before speculative decode (#37165)
|
2026-09-07 12:41:03 -07:00 |
|
|
Aurick Qiao
|
9a9e167179
|
[Bugfix] Fix full prefill CUDA graph padding and EAGLE capture (#35588)
|
2026-08-30 21:30:24 -07:00 |
|
|
Aurick Qiao
|
7276a30c45
|
[Fix] Support LSE on the RadixAttention extra-kwargs graph path (#35453)
|
2026-08-28 18:04:00 -07:00 |
|
|
Aurick Qiao
|
84a6f51bd6
|
Fix DeepSeek V4 multistream QKV buffer lifetime (#36547)
|
2026-08-28 10:10:36 +08:00 |
|
|
Aurick QiaoandYuwei An
|
26fd7fdaa2
|
[Feature] Support PP in full prefill CUDA graphs (#35451)
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
|
2026-08-27 17:32:00 -07:00 |
|
|
Aurick QiaoandYuwei An
|
58ecbba0bd
|
[Feature] Coordinate FullCG prefill across DP-attention ranks (#35640)
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
|
2026-08-26 02:16:02 -07:00 |
|
|
Aurick QiaoandYuwei An
|
3e30649064
|
[Fix] Harden FlashAttention CUDA graph metadata bounds (#35454)
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
|
2026-08-23 21:11:46 -07:00 |
|
|
Aurick Qiao
|
6185ed8011
|
Add registered short-conv tests and backend extensions (#34045)
|
2026-08-08 14:38:03 +08:00 |
|
|
Aurick Qiao
|
ad30a9958e
|
Fix dummy weight init for tensor subclasses (#29229)
|
2026-06-29 01:17:00 +08:00 |
|
|
Aurick Qiao
|
c06802dc16
|
Fix customized_info incremental streaming (#27205)
|
2026-06-05 21:55:01 +08:00 |
|
|
Aurick Qiao
|
bfccc8e504
|
Allow configuring NIXL backend parameters from env (#24169)
|
2026-05-01 18:30:43 -07:00 |
|
|
Aurick Qiao
|
cd2b2364ff
|
[Bugfix] fix model_config deletion (#22281)
|
2026-04-12 11:24:26 +08:00 |
|
|
Aurick Qiao
|
3178f3959f
|
Align incremental streaming logprobs with streamed output tokens (#21583)
|
2026-04-06 00:30:02 -07:00 |
|
|
Aurick Qiao
|
c2b3e42ad6
|
Fix sessions with mm inputs (#21269)
|
2026-03-26 17:38:23 -07:00 |
|
|
Aurick Qiao
|
a34e9ed64a
|
Add adjusted_filter_batch (#21260)
|
2026-03-26 10:59:05 +08:00 |
|
|
Aurick Qiao
|
53c1d8e963
|
Fix customized_info offset truncation (#21262)
|
2026-03-26 10:57:51 +08:00 |
|
|
Aurick Qiao
|
5c8e28698c
|
Add cleanup for _ATTN_TP in parallel_state.py (#19978)
|
2026-03-06 15:43:31 -08:00 |
|
|
Aurick Qiaoandhnyls2002
|
c6cb0c9649
|
[Session] Add streaming mode with SessionAwareCache fast path (#19171)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
|
2026-02-27 16:31:08 -08:00 |
|
|
Aurick Qiao
|
c1d529c196
|
Fix Session for multimodal and expose it through Engine (#18152)
|
2026-02-04 10:33:27 +08:00 |
|
|
Aurick Qiao
|
09a9d214f7
|
Pipe customized_info through CudaGraphRunner output (#17088)
|
2026-01-19 15:48:49 -08:00 |
|
|
Aurick Qiao
|
5b1215d9da
|
fix session request with None tokenizer (#16278)
|
2026-01-14 10:41:08 -08:00 |
|