Commits · 116f4be405ff8aaadbc885d8d527d1694c7fcf0a · OpenDAS / vllm_cscc

25 Mar, 2026 1 commit

[ROCm] Attention selector reordering (#36702) · 189ddefb

Gregory Shtrasberg authored Mar 25, 2026


Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>

189ddefb

20 Mar, 2026 1 commit
- [Attention] Support distinguishing between short extends and decodes (#37303) · e1d85e5c
  Lucas Wilkinson authored Mar 20, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  e1d85e5c
18 Mar, 2026 1 commit

[Bugfix] Fix KV scales inconsistency in fp8 MLA & FlashInfer kv_cache_dtype... · 577df69b

Andy Lo authored Mar 18, 2026


[Bugfix] Fix KV scales inconsistency in fp8 MLA & FlashInfer kv_cache_dtype "auto" leading to gibberish (#37054)
Signed-off-by: Andy Lo <andy@mistral.ai>

577df69b

16 Mar, 2026 1 commit
- [Bugfix] Fix GDN attention crash with mixed decode/spec-decode batches (#34871) · 116ed130
  haosdent authored Mar 16, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  116ed130
09 Mar, 2026 1 commit

[ROCm][CI] Fix ROCm attention backend validation for head sizes, block sizes,... · c174d54f

Andreas Karatzas authored Mar 09, 2026


[ROCm][CI] Fix ROCm attention backend validation for head sizes, block sizes, and compute capability checks (#36292)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>

c174d54f

07 Mar, 2026 2 commits
- [Perf] Support FP8 KV cache for Flashinfer MLA Sparse (#35891) · 379689d5
  Wei Zhao authored Mar 07, 2026
  
  379689d5
- [V0 Deprecation] Remove unused swap_space parameter (#36216) · 00b814ba
  lif authored Mar 07, 2026
```
Signed-off-by: majiayu000 <1835304752@qq.com>
Co-authored-by: mcelrath
```
  00b814ba
03 Mar, 2026 1 commit

TRTLLM gen-full attn Test Coverage (#34986) · e05cb3b9

ojhaanshika authored Mar 03, 2026


Signed-off-by: Anshika Ojha <anshikao@nvidia.com>
Co-authored-by: Anshika Ojha <anshikao@gb-nvl-059-compute09.nvidia.com>

e05cb3b9

24 Feb, 2026 2 commits

[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (#33726) · f5972a87

Benjamin Chislett authored Feb 24, 2026


Signed-off-by: Shahar Mor <smor@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>

f5972a87

[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

23 Feb, 2026 1 commit
- [Bugfix] Fix prefix caching for Mamba 'all' mode (Nemotron models) (#34874) · a2ba6a52
  haosdent authored Feb 24, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  a2ba6a52
20 Feb, 2026 1 commit
- [Test] Add FP8 KV Cache Testing for MLA Backends (#34473) · f24b2de3
  Wei Zhao authored Feb 20, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
```
  f24b2de3
14 Feb, 2026 1 commit
- [ROCm][CI] Guard sparse MLA backend imports for ROCm compatibility in tests (#34538) · b3c14229
  Andreas Karatzas authored Feb 14, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  b3c14229
12 Feb, 2026 1 commit

[Attention] Add FlashInfer Sparse MLA backend (#33451) · f2c47886

Matthew Bonanni authored Feb 12, 2026


Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

f2c47886

10 Feb, 2026 1 commit
- [SM100] Resubmit FMHA FP8 prefill for MLA (#31195) · 578977bb
  Pavani Majety authored Feb 10, 2026
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  578977bb
31 Jan, 2026 1 commit
- [Attention] Move MLA `forward` from backend to layer (#33284) · aaa901ad
  Matthew Bonanni authored Jan 30, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  aaa901ad
24 Jan, 2026 1 commit

[Performance] Split FlashAttn attention and cache update (#25954) · a28b94e6

ElizaWszola authored Jan 24, 2026


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

a28b94e6

22 Jan, 2026 1 commit
- [FlashMLA] Update FlashMLA to expose new arguments (#32810) · 889722f3
  Lucas Wilkinson authored Jan 21, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  889722f3
21 Jan, 2026 1 commit
- Update FlashMLA (#32491) · b4f64e5b
  Lucas Wilkinson authored Jan 20, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  b4f64e5b
19 Jan, 2026 1 commit

[BUGFIX] Fix `test_mla_backends.py`. Scale MLA projection weights to prevent... · 0727cc9e

Vadim Gimpelson authored Jan 19, 2026


[BUGFIX] Fix `test_mla_backends.py`. Scale MLA projection weights to prevent numerical instability  (#32529)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>

0727cc9e

13 Jan, 2026 2 commits
- [4/N][Attention] Move MLA common to model_executor (#32060) · 2263d44b
  Matthew Bonanni authored Jan 13, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  2263d44b
- [6/N][Attention] Move utils to more appropriate locations (#32215) · 98f60e5a
  Matthew Bonanni authored Jan 13, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  98f60e5a
12 Jan, 2026 2 commits
- [3/N][Attention] Move AttentionMetadata-related code from utils.py to backend.py (#32054) · 20228cb8
  Matthew Bonanni authored Jan 12, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  20228cb8
- [Bugfix] Fix stale SSM state for new Mamba requests scheduled as decode (#32118) · 8fb2c135
  Asaf Joseph Gardin authored Jan 12, 2026
```
Signed-off-by: Josephasafg <ajgard7@gmail.com>
```
  8fb2c135
09 Jan, 2026 1 commit
- [1/N][Attention] Restructure attention: move files (#31916) · 2612ba92
  Matthew Bonanni authored Jan 09, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  2612ba92
08 Jan, 2026 2 commits

[Misc] Fix `Current vLLM config is not set.` warnings, assert to avoid issues... · 6cdf015c

Lucas Wilkinson authored Jan 08, 2026


[Misc] Fix `Current vLLM config is not set.` warnings, assert to avoid issues in the future (#31747)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

6cdf015c

[ROCm][CI] Fix attention backend test flakiness from uninitialized KV cache memory (#31928) · 087a1389
Andreas Karatzas authored Jan 07, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
087a1389

06 Jan, 2026 1 commit

[Attention][1/n] Remove usage of deprecated `seq_lens_cpu` and... · e0327c9d

Lucas Wilkinson authored Jan 06, 2026


[Attention][1/n] Remove usage of deprecated `seq_lens_cpu` and `num_computed_tokens_cpu` CommonAttentionMetadata properties (#31773)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

e0327c9d

05 Jan, 2026 2 commits
- [v1] Add encoder-only/cross attention support to Triton Attention backend (#31406) · 6aa5b18e
  Isotr0py authored Jan 06, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  6aa5b18e
- [Platform] Deprecate seed_everything (#31659) · bb4337b3
  wangxiyuan authored Jan 05, 2026
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  bb4337b3
29 Dec, 2025 1 commit

[CI/ROCm] Fixing "V1 Test attention (H100)" test group. (#31187) · d63b9696

Alexei-V-Ivanov-AMD authored Dec 29, 2025

Signed-off-by: DCCS-4560 <alivanov@chi-mi325x-pod1-108.ord.vultr.cpe.ice.amd.com>
Signed-off-by: <>
Co-authored-by: DCCS-4560 <alivanov@chi-mi325x-pod1-108.ord.vultr.cpe.ice.amd.com>
Co-authored-by: root <root@chi-mi325x-pod1-108.ord.vultr.cpe.ice.amd.com>

d63b9696

23 Dec, 2025 1 commit
- Revert "[SM100] Enable fp8 compute for prefill MLA (#30746)" (#31197) · 3e102623
  Pavani Majety authored Dec 22, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  3e102623
22 Dec, 2025 1 commit
- [SM100] Enable fp8 compute for prefill MLA (#30746) · b10f41c8
  Pavani Majety authored Dec 22, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  b10f41c8
17 Dec, 2025 1 commit
- [Attention] Update tests to remove deprecated env vars (#30563) · 7eb6cb6c
  Matthew Bonanni authored Dec 17, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  7eb6cb6c
16 Dec, 2025 2 commits

[Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627) · 9fec0e13
Lucas Wilkinson authored Dec 16, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Stanislaw Wozniak <stw@zurich.ibm.com>
```
9fec0e13

[feature] extend DBO to XBO (#30120) · b9ff4f2a

jiangkuaixue123 authored Dec 16, 2025


Signed-off-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: root <root@hk01dgx028.cm.cluster>

b9ff4f2a

12 Dec, 2025 1 commit
- [Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532) · 3e41992f
  Lucas Wilkinson authored Dec 12, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  3e41992f
10 Dec, 2025 1 commit

[Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable... · abe93bce

Lucas Wilkinson authored Dec 09, 2025


[Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable true async spec-decode (#29624)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>

abe93bce

09 Dec, 2025 1 commit

[Attention] Make `split_decodes_and_prefills(..., require_uniform=True)` support padding (#29644) · aed84691

Lucas Wilkinson authored Dec 09, 2025


Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>

aed84691

07 Dec, 2025 1 commit
- Revert "[Renderer] Separate out `RendererConfig` from `ModelConfig` (#30145)" (#30199) · e83b7e37
  Cyrus Leung authored Dec 07, 2025
  
  e83b7e37