Commits · 8cd174fa358326d5cc4195446be2ebcd65c481ce · OpenDAS / vllm_cscc

26 Apr, 2026 1 commit
- [LoRA] MoE LoRA Refactor (#40338) · 8cd174fa
  Jee Jee Li authored Apr 26, 2026
  
  8cd174fa
20 Apr, 2026 1 commit

[BugFix][XPU] fix lora ops bgmv_expand size not match (#39989) · 898beca5

Liangliang Ma authored Apr 20, 2026


Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

898beca5

13 Apr, 2026 1 commit
- [LoRA] Support dual CUDA streams-Linear Layer (#35721) · 715681c1
  Jee Jee Li authored Apr 13, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  715681c1
25 Mar, 2026 1 commit
- [Bugfix][ROCm][MoE] Fix mxfp4 oracle regressions from #37128 (#37787) · 679c6a3e
  Andreas Karatzas authored Mar 24, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  679c6a3e
23 Mar, 2026 1 commit

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007) · dc6908ac

Ranran authored Mar 23, 2026


Signed-off-by: Ranran <1012869439@qq.com>
Signed-off-by: Ranran <hzz5361@psu.edu>
Signed-off-by: ran <hzz5361@psu.edu>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

dc6908ac

18 Mar, 2026 1 commit
- [LoRA] Make LoRA respect `language_model_only` (#37375) · 8c31f47c
  Jee Jee Li authored Mar 18, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  8c31f47c
13 Mar, 2026 1 commit
- Fp8 lora dense kernel (#35242) · b3ce711b
  yugong333 authored Mar 13, 2026
```
Signed-off-by: Yu Gong <yu3.gong@gmail.com>
```
  b3ce711b
09 Mar, 2026 1 commit
- Allow `markdownlint` to run locally (#36398) · a0f44bb6
  Harry Mellor authored Mar 09, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  a0f44bb6
02 Mar, 2026 1 commit

[Fix Bug]`num_active_loras` always equals to zero (#34119) · ada4f4fa

Runkai Tao authored Mar 02, 2026


Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

ada4f4fa

01 Mar, 2026 1 commit

Add TMA support to fused_moe_lora kernel (#32195) · 3ecd0bf9

gnovack authored Feb 28, 2026


Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

3ecd0bf9

26 Feb, 2026 1 commit
- [XPU][8/N] Fix kernel bugs in XPU LoRA and MOE LORA (#34115) · 9f9a675b
  Chaojun Zhang authored Feb 26, 2026
```
Signed-off-by: chzhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  9f9a675b
24 Feb, 2026 1 commit
- [LoRA] Update LoRA expand kernel block_n calculation (#32621) · c870eb9e
  Xin Yang authored Feb 23, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  c870eb9e
21 Feb, 2026 1 commit

[LoRA] Support Quantized Adapters (#30286) · a55caf6a

yugong333 authored Feb 20, 2026


Signed-off-by: Yu Gong <yu3.gong@gmail.com>
Signed-off-by: wz1qqx <ziqi.wang@novita.ai>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: wz1qqx <55830058+wz1qqx@users.noreply.github.com>
Co-authored-by: wz1qqx <ziqi.wang@novita.ai>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

a55caf6a

07 Feb, 2026 1 commit
- [Bugfix] Fix _fused_moe_lora_expand signature mismatch (#33821) · 3920cafd
  Xin Yang authored Feb 06, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  3920cafd
02 Feb, 2026 2 commits

Reduce the kernel overhead when num of active loras is smaller than max... · ffe1fc7a

yugong333 authored Feb 02, 2026


  Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)
Signed-off-by: Yu Gong <yu3.gong@gmail.com>

ffe1fc7a

Add unpermute-aware fused MoE LoRA path (#32655) · 7320ca39
Runkai Tao authored Feb 01, 2026
```
Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
```
7320ca39

28 Jan, 2026 1 commit

[lora/moe] Avoid extra intermediate buffer & Python slicing in expand phase... · f210f0b7

cwazai authored Jan 29, 2026


[lora/moe] Avoid extra intermediate buffer & Python slicing in expand phase when split_k == 1 (#32774)
Signed-off-by: 陈建华 <1647430658@qq.com>

f210f0b7

26 Jan, 2026 2 commits

[lora/moe] Improve fused MoE‑LoRA kernel indexing and memory access (#32770) · e33192b2

cwazai authored Jan 26, 2026


Signed-off-by: 陈建华 <1647430658@qq.com>
Signed-off-by: Yanwen Lin <lyw1124278064@gmail.com>
Signed-off-by: kimheesu <wlskaka4@gmail.com>
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Signed-off-by: Xin Yang <xyangx@amazon.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Ifta Khairul Alam Adil <ikaadil007@gmail.com>
Signed-off-by: Ifta khairul Alam Adil <25082512+ikaadil@users.noreply.gith...

e33192b2

Set splitk=1 for fused-moe-lora expand kernel (#32882) · ee484b3f

Danielle Robinson authored Jan 25, 2026


Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

ee484b3f

25 Jan, 2026 1 commit
- [BugFix] Add env variable to control PDL in LoRA (#32836) · 73b24346
  Jee Jee Li authored Jan 25, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  73b24346
24 Jan, 2026 2 commits
- Using max_loras + 1 to construct grid in fused_moe_lora (#32277) · d4dbb7af
  yugong333 authored Jan 24, 2026
```
Signed-off-by: Yu Gong <yu3.gong@gmail.com>
```
  d4dbb7af
- [Bugfix] Fix FusedMoE LoRA kernel offs_token out of bound value (#32279) · ecc3dd66
  Xin Yang authored Jan 23, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  ecc3dd66
16 Jan, 2026 1 commit
- [LoRA] Update LoRA expand kernel heuristic (#32425) · a884bc62
  Xin Yang authored Jan 16, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  a884bc62
13 Jan, 2026 1 commit
- [Misc] improve warning/assert messages (#32226) · 15b33ff0
  cjackal authored Jan 13, 2026
```
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
```
  15b33ff0
10 Jan, 2026 1 commit
- [LoRA][Perf] Improve FusedMoE LoRA performance for small rank (#32019) · 543c23be
  Xin Yang authored Jan 10, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  543c23be
07 Jan, 2026 1 commit

[Refactor][TPU] Remove torch_xla path and use tpu-inference (#30808) · e7596371

weiyu authored Jan 07, 2026


Signed-off-by: Wei-Yu Lin <weiyulin@google.com>
Signed-off-by: weiyu <62784299+weiyu0824@users.noreply.github.com>

e7596371

06 Jan, 2026 1 commit
- [LoRA]Disable linear LoRA kernel PDL (#31777) · cbd4690a
  Jee Jee Li authored Jan 06, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  cbd4690a
05 Jan, 2026 1 commit
- [LoRA] LoRA PDL improvement (#31660) · d5503ca7
  Jee Jee Li authored Jan 05, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  d5503ca7
23 Dec, 2025 1 commit
- [Feature] Batch invariant: Lora (#30097) · a37328fc
  liuquan authored Dec 23, 2025
```
Signed-off-by: quanliu <18646313696@163.com>
```
  a37328fc
18 Dec, 2025 1 commit

fused_moe_lora PDL improvements (#30716) · 5a3adf58

gnovack authored Dec 17, 2025


Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

5a3adf58

04 Dec, 2025 1 commit
- [Bugfix] Fix adapter_enabled IMA (#29977) · dd38ba3a
  Jee Jee Li authored Dec 04, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  dd38ba3a
19 Nov, 2025 1 commit
- add support for --fully-sharded-loras in fused_moe (#28761) · d69062c6
  gnovack authored Nov 19, 2025
```
Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  d69062c6
18 Nov, 2025 1 commit
- [Doc]: fix typos in various files (#28863) · 083cf326
  Didier Durand authored Nov 18, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  083cf326
13 Nov, 2025 1 commit
- [XPU] Support Triton path for LoRA operations on XPU (#28511) · dbbe0c75
  Fanli Lin authored Nov 13, 2025
```
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
```
  dbbe0c75
11 Nov, 2025 1 commit
- Fix Fused MoE LoRA Triton kernel bug (#28450) · 7dbe6d81
  Chaojun Zhang authored Nov 11, 2025
```
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
```
  7dbe6d81
10 Nov, 2025 1 commit
- [Kernel] Optimization of the mm_k operator. (#28280) · 40e2eeeb
  caozuoba authored Nov 11, 2025
```
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  40e2eeeb
07 Nov, 2025 1 commit
- [Kernel] LoRA triton kernels support PDL (#27402) · 21b82f4e
  Jee Jee Li authored Nov 07, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  21b82f4e
05 Nov, 2025 1 commit
- [Docs] Clean up README_TUNING.md (#28088) · 518ec6b7
  Michael Yao authored Nov 06, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  518ec6b7
04 Nov, 2025 2 commits

Load tuned fused_moe_lora shrink and expand kernel configs separately (#27435) · 2ec401bc
yugong333 authored Nov 04, 2025
```
Signed-off-by: Yu Gong <yu3.gong@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
2ec401bc

[LoRA] Lora shrink swizzle (#27694) · 6ddae740

li2haipeng authored Nov 03, 2025


Signed-off-by: li2haipeng <44383182+li2haipeng@users.noreply.github.com>
Signed-off-by: Haipeng Li <li2haipeng@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

6ddae740