Commits · 2dde535df1b736315e56eace0fa1923fe0beffc5 · OpenDAS / vllm_cscc

07 Mar, 2026 3 commits
- [compile] Split compile/warmup monitoring (#36098) · 2dde535d
  Richard Zou authored Mar 07, 2026
  
  2dde535d
- [Core] NGram GPU Implementation compatible with Async Scheduler (#29184) · a6be75db
  PatchyTIS authored Mar 08, 2026
  
  a6be75db
- [UX][Startup] Account for CUDA graphs during memory profiling (#30515) · ebb9cc5f
  Matthew Bonanni authored Mar 07, 2026
  
  ebb9cc5f
06 Mar, 2026 1 commit
- [compile] Stop unconditionally patching constrain_to_fx_strides (#36152) · 54756b61
  Richard Zou authored Mar 06, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  54756b61
05 Mar, 2026 3 commits
- [compile] Consistent compiler config for saved/loaded vllm backends. (#35810) · a97954b6
  Zhengxu Chen authored Mar 05, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  a97954b6
- [compile] Fix extra cache save on warm start. (#35921) · dd6dbd93
  Zhengxu Chen authored Mar 04, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  dd6dbd93
- [compile] Reduce log spam from compile. (#36044) · 2ed4722e
  Zhengxu Chen authored Mar 04, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  2ed4722e
04 Mar, 2026 2 commits

[torch.compile] Stop lazily compiling (#35472) · 5569f521
Richard Zou authored Mar 04, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
5569f521

[Hardware] Replace `torch.cuda.empty_cache` with `torch.accelerator.empty_cache` (#30681) · 16d2ad1d

Kunshang Ji authored Mar 04, 2026


Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

16d2ad1d

03 Mar, 2026 1 commit

[ROCm] [CI] Add new fusion test cases that are relevant to vLLM IR Ops (#34307) · fb7fdc49

TJian authored Mar 03, 2026


Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>

fb7fdc49

02 Mar, 2026 2 commits
- [torch.compile] Improve cold and warm start compile tests (#35709) · d1a6e96d
  Richard Zou authored Mar 02, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  d1a6e96d
- [Misc] Cleanup useless `current_platform` import (#35715) · 510bc9e1
  wangxiyuan authored Mar 02, 2026
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  510bc9e1
28 Feb, 2026 1 commit

[1/N] Elastic EP Milestone 2 (#34861) · dea26833

Itay Alroy authored Feb 28, 2026


Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>

dea26833

27 Feb, 2026 4 commits
- [ROCm]: fix aiter rope functionalization (#35533) · e3691988
  Rohan Potdar authored Feb 27, 2026
```
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
```
  e3691988
- [Bugfix] Add monkeypatch to prevent race condition from writing (#35420) · 234a65b7
  Lucas Kabela authored Feb 27, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  234a65b7
- [compile] Fix caching error over pytree slice node. (#35308) · 29b35477
  Zhengxu Chen authored Feb 27, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  29b35477
- [Bugfix] Use 'sum' reduction instead of 'avg' in Async TP reduce-scatter (#33088) · 07bdabef
  Wang Xingran authored Feb 27, 2026
```
Signed-off-by: Xingran Wang <wangxingran123456@outlook.com>
Signed-off-by: Hongjian Zhang <hirokenovo@gmail.com>
Co-authored-by: Hongjian Zhang <hirokenovo@gmail.com>
```
  07bdabef
26 Feb, 2026 3 commits

[torch.compile] Sequence Parallelism threshold compile ranges (#28672) · 9d379410

Jason Li authored Feb 25, 2026


Signed-off-by: jasonlizhengjian <jasonlizhengjian@gmail.com>
Signed-off-by: Jason Li <jasonlizhengjian@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

9d379410

[Kernel] Refactor FlashInfer allreduce for mnnvl backend (#34109) · 71dfce6a

Hanjie Qiu authored Feb 25, 2026


Signed-off-by: hjjq <50634613+hjjq@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>

71dfce6a

[offloader] v2: Hide weight onloading latency via prefetching (#29941) · 6831650c

Ming Yang authored Feb 25, 2026


Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

6831650c

25 Feb, 2026 3 commits
- [Bugfix] Gracefully disable AllReduceFusionPass on GPUs without multicast support (#35085) · 0788ff0a
  haosdent authored Feb 25, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  0788ff0a
- [compile] Improve error message during artifacts load failure. (#35115) · 5cc29cfb
  Zhengxu Chen authored Feb 25, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  5cc29cfb
- [ROCm]: Enable customop and rope+kvcache fusion for AITER RoPE (#35180) · f38f8c97
  Rohan Potdar authored Feb 24, 2026
```
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
```
  f38f8c97
24 Feb, 2026 2 commits

[compile] Save aot compile artifacts atomically. (#35117) · c77f3e12
Zhengxu Chen authored Feb 24, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
c77f3e12

[ROCm] AITER fused RoPE+KVCache (#33443) · 2ff4e511

Rohan Potdar authored Feb 23, 2026


Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: charlifu <charlifu@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>

2ff4e511

20 Feb, 2026 2 commits
- [compile] Fix torch.compile time discrepancy in logging. (#34912) · f8639940
  Zhengxu Chen authored Feb 20, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  f8639940
- [compile] Move torch_aot_compile directory under torch_compile_cache (#34831) · e4a5d8c6
  Zhengxu Chen authored Feb 20, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  e4a5d8c6
19 Feb, 2026 1 commit
- fix(docs): fix typos in comments and docstrings (#34836) · ad5aa6bd
  Manrique Vargas authored Feb 19, 2026
```
Signed-off-by: machov <mv1742@nyu.edu>
```
  ad5aa6bd
18 Feb, 2026 1 commit
- [Bugfix] Fix quant RMS norm fusion for quantization with TMA-aligned scales (#33255) · a88b3be7
  ElizaWszola authored Feb 18, 2026
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  a88b3be7
11 Feb, 2026 1 commit
- [torch.compile] Stop doing unnecessary FakeTensorProp in PiecewiseCompileInterpreter (#34093) · e30cedd4
  Richard Zou authored Feb 10, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  e30cedd4
10 Feb, 2026 1 commit
- [torch.compile] Disable recursive pre_grad_passes (#34092) · 341eed3d
  Richard Zou authored Feb 10, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  341eed3d
09 Feb, 2026 2 commits
- [torch.compile][Fusion] Fix attention fusion pass removing kv_udpate op. (#33945) · bb9f9730
  Charlie Fu authored Feb 09, 2026
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  bb9f9730
- [Kernel] FlashInfer: switch allreduce fusion to unified API (#33985) · d4f123cc
  Mohammad Miadh Angkad authored Feb 09, 2026
```
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
```
  d4f123cc
08 Feb, 2026 2 commits
- [Release 2.10] Update to Torch 2.10 - final release (#30525) · f97ca671
  Andrey Talman authored Feb 08, 2026
  
  f97ca671
- [ROCm][Bugfix] fix act_quant_fusion module import error (#34069) · ab10d798
  Andreas Karatzas authored Feb 07, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  ab10d798
07 Feb, 2026 2 commits
- [torch.compile] Stop compiling identical artifacts (#34003) · 81fe69ca
  Richard Zou authored Feb 07, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  81fe69ca
- [Bugfix] Fix QK Norm+RoPE fusion pattern matching on B200+FP8 (#33967) · 90607718
  Ikenna authored Feb 06, 2026
```
Signed-off-by: Ikenna <ikennachifo@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  90607718
06 Feb, 2026 3 commits
- [Log] Optimize duplicate startup log (#33944) · 67a746e8
  Wentao Ye authored Feb 06, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  67a746e8
- [torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731) · ac32e66c
  Luka Govedič authored Feb 06, 2026
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: ProExpertProg <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  ac32e66c
- [Feature] OTEL tracing during loading (#31162) · 325ab6b0
  emricksini-h authored Feb 06, 2026
  
  325ab6b0