hsliuustc0106
c9bb65902e
[Model] Learn the retention budget directly from observed peaks
...
Drop the staged-bytes seed per review direction: the budget is now
min(observed_peak * 1.25, 25% of device capacity), nothing else. A cold
start pays one release per observation step while the peak climbs (two on
the validated MiniMax workload), then boundaries retain steadily; the 5%
free floor and capacity cap are unchanged. The staged-byte ledger remains
only to detect full detachment, which now resets the observed peak so one
workload cannot permanently influence another. Trade-off accepted per
review: lower reserved memory and a simpler policy over a flush-free
first request.
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-26 13:43:00 +08:00
hsliuustc0106
b78db6036a
[Model] Fix adaptation test fixture so the capacity cap does not bind
...
The fixture reported device capacity 100, making the 25% cap 25 — below
the learned budget of 37 — so the post-adaptation checks released again
and the test failed. Raise the fixture capacity to 400 so the cap stays
above the learned budget and the test isolates peak adaptation; verified
against the real suite on the L20X validation host (15 passed).
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-26 13:12:55 +08:00
hsliuustc0106
27f9726a6a
[Model] Derive the retention budget from observed boundary peaks
...
The staged-bytes seed left the transient half of the working set to a
guessed multiplier, and that half scales with the running workload rather
than the model topology. Track the largest cached-but-unallocated value
observed at any component boundary instead: the budget is the larger of
the seed and the observed peak times a 1.25 margin, still capped at a
quarter of device capacity. A workload that outgrows the seed pays one
release while the observation lands, then retains steadily. No warmup
flag is needed and no user-chosen fraction exists.
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-26 12:52:19 +08:00
hsliuustc0106
c5295f3ffe
[Model] Cap derived cache budget and account for stager detach
...
Address review on #6629 :
- Cap the derived retention budget at a quarter of device capacity so a
large staged total cannot monopolize a small device; the multiplier
itself stays pending an instrumented target run.
- Log every release decision (reason, cached bytes, effective budget and
cap, staged total, free/total memory) and every staging OOM retry with
its staged byte total, so a single target run validates the headroom
multiplier directly.
- Make stager detach symmetric: set_cache_retention now shrinks the
previous cache's budget before growing the new one, so cache -> None ->
same cache counts the staged bytes exactly once (regression test added).
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-26 11:12:09 +08:00
hsliuustc0106
ba5943dddb
[Model] Derive MiniMax-H3 DLO component cache budget from staged bytes
...
Replace BoundedAllocatorCache's device-capacity fraction bound (25% of
total memory) with a budget derived from the model topology: each attached
PinnedModuleStager reports its unique staged storage bytes once, and the
retention ceiling is that total times a fixed 2.0 headroom multiplier
covering allocator fragmentation and transient storages freed at component
boundaries. The 5% physically-free floor is unchanged.
The budget therefore scales with the staged components instead of device
capacity, so no user-chosen fraction is needed and behavior is identical
across differently sized devices with the same model. Re-attaching the
same cache does not double count; a second stager grows the budget by its
own bytes.
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-26 09:49:55 +08:00
Hongsheng Liu and hsliuustc0106
c608910d20
[Diffusion] Register HWR mmap for direct DLO H2D ( #6591 )
...
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Signed-off-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com >
Co-authored-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com >
2026-08-25 23:30:11 +08:00
Hongsheng Liu
5a8b81ebeb
[Model] Optimize MiniMax-H3 DLO component lifecycle ( #6526 )
...
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-25 23:13:41 +08:00
wangyu and amy-why-3459
4af0ddc1c2
[Test] Cleanup for helpers ( #6523 )
...
Signed-off-by: wangyu <410167048@qq.com >
Signed-off-by: [Your Name] <your.email@example.com >
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com >
2026-08-25 09:10:17 +08:00
Hongsheng Liu and hsliuustc0106
8360346a66
[Diffusion] Integrate no-AllGather DLO with Host Weight Runtime ( #6486 )
...
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Signed-off-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com >
Co-authored-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com >
2026-08-25 08:03:53 +08:00
Nick Cao
b2c9376539
[BugFix] Eliminate distributed test port race by switching to file:// rendezvous ( #6468 )
...
Signed-off-by: Nick Cao <ncao@redhat.com >
2026-08-23 07:08:44 +08:00
R0CKSTAR
260db8bab5
[Bugfix][Diffusion] Fix MiniMax-H3 model-level CPU offload residency ( #6072 )
...
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
2026-08-21 10:30:53 +00:00
Hongsheng Liu
284e05c88b
[Core] Support online FP8 with DLO AllGather ( #6279 )
...
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-18 23:48:07 +08:00
Hongsheng Liu
9d2bb23ff6
[Diffusion] Add loader-owned host-weight plans for DLO (TP=1) ( #6213 )
...
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-16 11:02:38 +08:00
SYLAR and Hongsheng Liu
d1e230c95b
[Diffusion][Quantization] Enable MiniMax-H3 global FP8 with DLO ( #5910 )
...
Signed-off-by: lishunyang12 <lishunyang12@163.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-15 23:01:26 +08:00
fcf1085395
[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up ( #5146 )
...
Signed-off-by: Boao Shi <aoibosh@connect.hku.hk >
Signed-off-by: bowieshi <aoibosh@connect.hku.hk >
Signed-off-by: princepride <wangzhipeng628@gmail.com >
Signed-off-by: R2-Y <ruiruyang2@gmail.com >
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com >
Signed-off-by: Shi Boao Bowie <aoibosh@connect.hku.hk >
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com >
Co-authored-by: ruirui(rein) yang <73573651+R2-Y@users.noreply.github.com >
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com >
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-12 22:58:23 +08:00
SYLAR and lishunyang12
1c2a81f6d8
feat(minimax-h3): enable 2x RTX 4090/5090 with DLO ( #5764 )
...
Signed-off-by: lishunyang12 <lishunyang03@gmail.com >
Signed-off-by: lishunyang12 <lishunyang12@163.com >
Co-authored-by: lishunyang12 <lishunyang03@gmail.com >
2026-08-06 09:02:29 +08:00
ooooooye
6510de344e
[Bugfix][Diffusion] Fix DLO AllGather size mismatch for models with h… ( #5802 )
...
Signed-off-by: brandneway <gyuan4892@gmail.com >
2026-08-05 09:32:41 +00:00
evanchueng and david6666666
744c65b730
[Feature] Distributed layerwise offload with DP multi-concurrency + mmap weight… ( #5397 )
...
Signed-off-by: evanchueng <evanchueng@outlook.com >
Signed-off-by: david6666666 <530634352@qq.com >
Co-authored-by: david6666666 <530634352@qq.com >
2026-07-30 13:35:38 +00:00
wangyu
7c17111ff5
[Refactor][CI] Reorganize test tree, and move slow e2e to weekly ( #4951 )
...
Signed-off-by: wangyu <410167048@qq.com >
2026-07-29 23:53:03 +08:00
wangyu
907f932b72
[CI][Test] Tier diffusion offloader CI and reduce gpu_4_queue merge usage and fix #5182 ( #5185 )
...
Signed-off-by: wangyu <410167048@qq.com >
2026-07-18 17:15:17 +08:00
Rahul Steiger
66b9ad287a
Extend Cosmos3 CPU offloading to component and layerwise paths ( #4695 )
2026-07-13 09:48:53 +00:00
zhumingjue138
2d2258890b
[CI] skip ci for issue 4537 ( #4538 )
...
Signed-off-by: zhumingjue <zhumingjue@huawei.com >
2026-06-18 17:53:34 +08:00
Nick Cao and Claude
e957d16f8d
[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery ( #3076 )
...
Signed-off-by: Nick Cao <ncao@redhat.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-06-17 21:33:06 +08:00
+1
f92d84fcf9
[Rebase] Rebase to vllm releases/v0.22.0 ( #3891 )
...
Signed-off-by: tzhouam <tzhouam@connect.ust.hk >
Signed-off-by: ZhengWG <zwg0606@gmail.com >
Signed-off-by: david6666666 <530634352@qq.com >
Signed-off-by: Yueqian Lin <linyueqian@outlook.com >
Signed-off-by: nainiu258 <cperfect02@163.com >
Signed-off-by: nainiu258 <101917677+nainiu258@users.noreply.github.com >
Signed-off-by: JasonJ2021 <jasonj@zju.edu.cn >
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk >
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
Co-authored-by: skf <54565339+skf-1999@users.noreply.github.com >
Co-authored-by: Zheng Wengang <zwg0606@gmail.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com >
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com >
Co-authored-by: Yueqian Lin <linyueqian@outlook.com >
Co-authored-by: nainiu258 <101917677+nainiu258@users.noreply.github.com >
Co-authored-by: Jason <72191212+JasonJ2021@users.noreply.github.com >
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com >
2026-06-01 11:08:12 +08:00
+20
eb4e60ee64
[Rebase] Rebase to vllm v0.21.0 ( #3530 )
...
Signed-off-by: tzhouam <tzhouam@connect.ust.hk >
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk >
Signed-off-by: NumberWan <wantszkin2003@gmail.com >
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com >
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com >
Signed-off-by: Dnoob <dxpouo@gmail.com >
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com >
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com >
Signed-off-by: rein yang <ruiruyang2@gmail.com >
Signed-off-by: Nick Cao <ncao@redhat.com >
Signed-off-by: zhumingjue <zhumingjue@huawei.com >
Signed-off-by: Ricardo Noriega De Soto <rnoriega@redhat.com >
Signed-off-by: lyj-jjj <liuyingjun5@huawei.com >
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
Signed-off-by: wangyu <410167048@qq.com >
Signed-off-by: weizhoublue <weizhoublue@github.com >
Signed-off-by: weizhou.lan@daocloud.io <weizhou.lan@daocloud.io >
Signed-off-by: dengyunyang <584797741@qq.com >
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com >
Signed-off-by: David Chen <530634352@qq.com >
Signed-off-by: Jie Liu <33612777+keeper-jie@users.noreply.github.com >
Signed-off-by: Yueqian Lin <linyueqian@outlook.com >
Signed-off-by: princepride <wangzhipeng628@gmail.com >
Signed-off-by: natureofnature <wzliu@connect.hku.hk >
Signed-off-by: bjf-frz <frz123db@gmail.com >
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com >
Signed-off-by: KexiongYu <yukexiong1@huawei.com >
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com >
Signed-off-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com >
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
Co-authored-by: NumberWan <wantszkin2003@gmail.com >
Co-authored-by: dsinghvi <divyanshsinghvi@gmail.com >
Co-authored-by: Dnoob <dxpouo@gmail.com >
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com >
Co-authored-by: Samit <285365963@qq.com >
Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com >
Co-authored-by: Nick Cao <ncao@redhat.com >
Co-authored-by: zhumingjue138 <zhumingjue@huawei.com >
Co-authored-by: Ricardo Noriega <rnoriega@redhat.com >
Co-authored-by: lyj-jjj <liuyingjun5@huawei.com >
Co-authored-by: Cursor <cursoragent@cursor.com >
Co-authored-by: gcanlin <canlinguosdu@gmail.com >
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com >
Co-authored-by: weizhoublue <45163302+weizhoublue@users.noreply.github.com >
Co-authored-by: weizhoublue <weizhoublue@github.com >
Co-authored-by: dengyunyang <584797741@qq.com >
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com >
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com >
Co-authored-by: Jie Liu <33612777+keeper-jie@users.noreply.github.com >
Co-authored-by: Yueqian Lin <linyueqian@outlook.com >
Co-authored-by: NATURE <wzliu@connect.hku.hk >
Co-authored-by: bjf-frz <frz123db@gmail.com >
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com >
Co-authored-by: Y. Fisher <yukexiong1@huawei.com >
Co-authored-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com >
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com >
2026-05-16 18:18:43 +08:00
Nick Cao and Claude
65bc968465
[Refactor] Rename SupportsModuleOffload to SupportsComponentDiscovery ( #3354 )
...
Signed-off-by: Nick Cao <ncao@redhat.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-05-08 14:16:49 +00:00
wangyu and Huang, Zeyu
6f2ad7b403
[Test] Unify L2/L3 test layout, Buildkite steps, and test helpers ( #2556 )
...
Signed-off-by: wangyu <410167048@qq.com >
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com >
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com >
Co-authored-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com >
2026-05-08 14:12:23 +08:00
Nick Cao and Claude
e3b0afbb97
[Refactor] Let diffusion pipelines declare offloadable modules via SupportsModuleOffload ( #2427 )
...
Signed-off-by: Nick Cao <ncao@redhat.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-04-23 04:23:00 +08:00
Yuanheng Zhao
e0cdbe9a5d
[Misc] Cleanup: use consistent pytest-mock in unit tests ( #2698 )
...
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com >
2026-04-13 19:21:42 +08:00
Lancer and Didan Deng
328de586aa
[Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU ( #1486 )
...
Signed-off-by: Lancer <maruixiang6688@gmail.com >
Signed-off-by: Lancer <402430575@qq.com >
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com >
2026-04-06 11:49:35 +08:00
Lancer
dd0b6fd4e8
[Bugfix] Fix layer-wise offload incompatibility with HSDP ( #2021 )
...
Signed-off-by: Lancer <maruixiang6688@gmail.com >
2026-04-01 09:25:34 +08:00
Lancer and gcanlin
4cfa9bf843
[Bugfix] fix offload and hsdp incompatibility ( #1888 )
...
Signed-off-by: Lancer <maruixiang6688@gmail.com >
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
Co-authored-by: gcanlin <canlinguosdu@gmail.com >
2026-03-24 14:50:57 +08:00
