Commits · 519ef9a91111d2d6f8545c8a6b2c1a28d87309fa · OpenDAS / vllm_cscc

14 Dec, 2025 3 commits
- [Bugfix] Fix fusion for VL models (#30244) · 994acec0
  ElizaWszola authored Dec 14, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
  994acec0
- [torch.compile] Add encoder tag for compilation (#30489) · 3224ea99
  Ilya Markov authored Dec 14, 2025
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
  3224ea99
- enable unbacked with aot_compile (#30462) · f569c654
  Laith Sakka authored Dec 14, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
  f569c654
13 Dec, 2025 1 commit
- set assume_32bit_indexing and pass unbacked hints (#30459) · 763963aa
  Laith Sakka authored Dec 13, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
  763963aa
12 Dec, 2025 1 commit
- [compile] Parse compile range cache keys as Range during cache loading. (#30516) · fe178710
  Zhengxu Chen authored Dec 11, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  fe178710
11 Dec, 2025 1 commit
- [compile] Stop one-off setting enable_aot_compile and use context manager instead. (#30503) · 92fea56f
  Zhengxu Chen authored Dec 11, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  92fea56f
09 Dec, 2025 2 commits

[Rocm][torch.compile] Adding layernorm + fp8 block quant and silu + fp8 block... · 3c680f4a

Charlie Fu authored Dec 09, 2025


[Rocm][torch.compile] Adding layernorm + fp8 block quant and silu + fp8 block quant for Aiter (#25693)
Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Charlie Fu <Charlie.Fu@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: wuhuikx <hattie.wu@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>

3c680f4a

[BugFix] Fix non detected failing tests (#30277) · 0b6a8a30
Ilya Markov authored Dec 09, 2025
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
0b6a8a30

08 Dec, 2025 3 commits
- Add evaluate_guards option to DynamicShapesConfig (#27432) · 87aee9ed
  Laith Sakka authored Dec 08, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
  87aee9ed
- [ROCm] Guard group quant RMS norm fusion patterns (#30239) · eb1051fb
  Ye (Charlotte) Qi authored Dec 08, 2025
  
  eb1051fb
- [Bugfix] fix fuse_allreduce_rms when tp =1 (#30178) · d1432712
  Jiangyun Zhu authored Dec 08, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  d1432712
07 Dec, 2025 1 commit

[Performance] Fused blockwise quant RMS norm (#27883) · af0444bf

ElizaWszola authored Dec 07, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>

af0444bf

05 Dec, 2025 4 commits

[Compile] Conditional compilation. Introduce compile_ranges (#24252) · 4e26d3b0

Ilya Markov authored Dec 05, 2025


Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>

4e26d3b0

[bugfix] Pass globals to aot_compiled function (#29428) · e7296b08
Angela Yi authored Dec 05, 2025
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
e7296b08

[Feature] Add Layer-wise NVTX Support (#29990) · c2894d38

Max Hu authored Dec 05, 2025


Signed-off-by: Max Hu <hyoung2991@gmail.com>
Signed-off-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>

c2894d38

Do not guard during noop elimination pass (#30095) · 5867819e
Laith Sakka authored Dec 04, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
5867819e

04 Dec, 2025 1 commit
- [aot_compile]change VLLM backend to read fake args from example_value (#29104) · 1f0d1845
  Laith Sakka authored Dec 04, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
  1f0d1845
03 Dec, 2025 4 commits

[Bugfix] Fix flashinfer ar+norm kernel not available issue (#29960) · afe9eb40
elvischenv authored Dec 04, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
afe9eb40
Add logging for cudagraph related info (#29825) · 69520bc6
Yong Hoon Shin authored Dec 02, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
69520bc6

[Bugfix] Defunctionalize TRTLLM AR+Norm op for avoiding extra clone kernel before it (#29631) · c719c405

elvischenv authored Dec 03, 2025

Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

c719c405

[Core] Rename PassConfig flags as per RFC #27995 (#29646) · d7284a26

Arpit Khandelwal authored Dec 02, 2025


Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

d7284a26

28 Nov, 2025 1 commit
- [Doc]: fixing typos in multiple files. (#29685) · fae69430
  Didier Durand authored Nov 28, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  fae69430
26 Nov, 2025 2 commits

[Attention] Remove imports from `vllm/attention/__init__.py` (#29342) · 430dd4d9
Matthew Bonanni authored Nov 26, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
430dd4d9

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795) · 56531b79

George D. Torres authored Nov 25, 2025


Signed-off-by: George D. Torres <gdavtor@gmail.com>
Signed-off-by: George D. Torres <41129492+geodavic@users.noreply.github.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

56531b79

25 Nov, 2025 2 commits

[Compile] Refactor. Move PostGradPassManager out of Compilation config (#29340) · e7d77627
Ilya Markov authored Nov 25, 2025
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
e7d77627

Allow oot custom compiler extension via CompilerInterface (#28623) · 888152bf

Icey authored Nov 25, 2025


Signed-off-by: wxsIcey <1790571317@qq.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Signed-off-by: Icey <1790571317@qq.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

888152bf

24 Nov, 2025 1 commit

Add option to use unbacked, and backed size obl dynamic shapes for more sounds... · 7a228b53

Laith Sakka authored Nov 24, 2025


Add option to use unbacked, and backed size obl dynamic shapes for more sounds compilation. (#26199)
Signed-off-by: Laith Sakka <lsakka@meta.com>

7a228b53

22 Nov, 2025 1 commit
- [Bugfix]Fix a conditional to not check zero value (#28754) · 933f67ec
  Yanan Cao authored Nov 21, 2025
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  933f67ec
21 Nov, 2025 1 commit

[kernel][perf] support uncontiguous input for rms_norm kernel (#28103) · a982f5b5

zhrrr authored Nov 21, 2025


Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
Signed-off-by: izhuhaoran <izhuhaoran@qq.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

a982f5b5

20 Nov, 2025 1 commit
- Fixes bench (#29058) · 3fd74189
  Driss Guessous authored Nov 20, 2025
```
Signed-off-by: drisspg <drisspguessous@gmail.com>
```
  3fd74189
19 Nov, 2025 1 commit

[torch.compile] caching of config fields should be opt-out by default (#26468) · 1ffe934c

vnadathur authored Nov 19, 2025

Signed-off-by: vnadathur <glvikramn@gmail.com>
Signed-off-by: WorldExplored <srreyansh.sethi@gmail.com>
Signed-off-by: Srreyansh Sethi <srreyansh.sethi@gmail.com>
Signed-off-by: Srreyansh Sethi <107075589+WorldExplored@users.noreply.github.com>
Co-authored-by: WorldExplored <srreyansh.sethi@gmail.com>
Co-authored-by: Srreyansh Sethi <107075589+worldexplored@users.noreply.github.com>
Co-authored-by: vnadathur <236933696+vnadathur@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

1ffe934c

17 Nov, 2025 1 commit
- [XPU] work around for sp, avoid custom op import error (#28822) · 1b82fb0a
  Kunshang Ji authored Nov 17, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  1b82fb0a
15 Nov, 2025 2 commits

[Doc]: fix typos in various files (#28567) · 2bb4435c
Didier Durand authored Nov 15, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
2bb4435c

[compile] Enable sequence parallelism matching w/o custom ops enabled (#27126) · f36292db

Angela Yi authored Nov 15, 2025


Signed-off-by: angelayi <yiangela7@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>

f36292db

14 Nov, 2025 1 commit
- Avoid bytecode hook and simplify TorchCompileWrapperWithCustomDipatch (#25110) · 2e0ad629
  Laith Sakka authored Nov 14, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
  2e0ad629
13 Nov, 2025 1 commit
- [Bugfix] Eliminate tuple inputs to submodules in graph partitioning (#28533) · 262d263f
  Yanan Cao authored Nov 13, 2025
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  262d263f
12 Nov, 2025 1 commit
- [Frontend] Change CompilationMode to a proper Enum (#28165) · 48c87936
  Yanan Cao authored Nov 11, 2025
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  48c87936
11 Nov, 2025 1 commit
- [Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165) · 68c09efc
  zhrrr authored Nov 12, 2025
```
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
```
  68c09efc
10 Nov, 2025 1 commit

[PERF] Allreduce fusion. Support torch native matching. Tuning of the thresholds (#24248) · d17ecc6b

Ilya Markov authored Nov 11, 2025

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

d17ecc6b

08 Nov, 2025 1 commit
- remove resolve_op_overloads and use splitting_ops directly (#28081) · b158df28
  Boyuan Feng authored Nov 07, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  b158df28