Commits · 2b28b9b269e18cfe42c7e945d1da8d1c40989efa · OpenDAS / vllm_cscc

09 Mar, 2026 1 commit
- [Attention][Perf] Optimize cp_gather_and_upconvert_fp8_kv_cache - DeepSeek-v3.2 (#35290) · 2b28b9b2
  Roberto L. Castro authored Mar 09, 2026
```
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  2b28b9b2
05 Mar, 2026 2 commits

[Bugfix][CI] fix typos (#34934) · 6a895197

Jiayi Yan authored Mar 06, 2026

Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

6a895197

[Perf] Use dummy M for weight prepacking on x86 (#35890) · 8e782013
Tianmu Li authored Mar 04, 2026
```
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
```
8e782013

02 Mar, 2026 1 commit

[Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448) · cb21972a

EdalatiAli authored Mar 02, 2026


Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

cb21972a

01 Mar, 2026 1 commit
- [Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798) · bbf81f9a
  Asaf Gardin authored Mar 01, 2026
```
Signed-off-by: Josephasafg <ajgard7@gmail.com>
```
  bbf81f9a
28 Feb, 2026 3 commits

Add padding support to wvSplitK solution for skinny GEMMs (#33762) · 7600642e
Hashem Hashemi authored Feb 28, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
7600642e
[CI/Build] CPU release supports both of AVX2 and AVX512 (#35466) · 90805ff4
Ma Jian authored Feb 28, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: jiang1.li <jiang1.li@intel.com>
```
90805ff4

[Refactor][Kernel] Add global helper to deduplicate vectorized memory ops (#35105) · a201ad72

Roberto L. Castro authored Feb 28, 2026

Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>

a201ad72

27 Feb, 2026 1 commit
- [Performance] Cublas Bf16 Gate with Fp32 Output (#35121) · 38c498b8
  roikoren755 authored Feb 27, 2026
```
Signed-off-by: Roi Koren <roik@nvidia.com>
```
  38c498b8
26 Feb, 2026 3 commits
- [WideEP] Remove pplx all2all backend (#33724) · eb19955c
  Tyler Michael Smith authored Feb 26, 2026
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  eb19955c
- [Bugfix] Fix uint32 overflow in Mamba selective scan state pointer arithmetic (#35275) · ec13e549
  Asaf Gardin authored Feb 26, 2026
```
Signed-off-by: Josephasafg <ajgard7@gmail.com>
```
  ec13e549
- [BugFix] Fix fp4 quant kernel on CUDA 12.8 (#35210) · 86c3b5a8
  Roberto L. Castro authored Feb 26, 2026
```
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
```
  86c3b5a8
25 Feb, 2026 2 commits
- [Perf] Optimize FP8 gemm of sm120. (#34424) · cd436736
  wenshuai authored Feb 25, 2026
```
Signed-off-by: wenshuai <wenshuai@xiaomi.com>
```
  cd436736
- [Bugfix] Fix expert_ids padding values in moe_align_block_size kernel (#35161) · 3bbb2046
  Xin Yang authored Feb 24, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  3bbb2046
24 Feb, 2026 3 commits
- Convert wvSplitKQ to 16x16 MFMA in prep for mi4xx. (#34100) · a0e50a42
  Hashem Hashemi authored Feb 24, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
  a0e50a42
- [CPU][Perf] Accelerate Attention head for s390x using vector intrinsics (#34434) · 34ce0ffd
  R3hankhan authored Feb 24, 2026
```
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
```
  34ce0ffd
- [Bugfix] Fix DSV3 kernels breaking _C and _moe_C on unsupported arches (#35123) · 3ef9fd0f
  Michael Goin authored Feb 23, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  3ef9fd0f
23 Feb, 2026 1 commit
- [ModelBash][DSV3] Add TRTLLM DSV3 Router GEMM kernel (6% B1 Speedup) (#34302) · 8435b2e0
  Robert Shaw authored Feb 23, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  8435b2e0
21 Feb, 2026 1 commit

[Bugfix] Gate 256-bit instructions to CUDA 12.9+ (#34791) · 272b535a

Huy Do authored Feb 21, 2026


Signed-off-by: Huy Do <huydhn@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

272b535a

20 Feb, 2026 1 commit
- [Kernel] Optimize grouped topk kernel (#34206) · b1c4f0b2
  Xin Yang authored Feb 20, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  b1c4f0b2
18 Feb, 2026 3 commits
- [Model Bash] DeepSeek R1 BF16 Min Latency QKV A GEMM (0.5% E2E Speedup) (#34758) · 6874638b
  Robert Shaw authored Feb 18, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  6874638b
- [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
- [BugFix] [Build] fix string literals comparison in indexer_k_quant_and_cache calling site (#34653) · 4a00a511
  Hongxia Yang authored Feb 17, 2026
```
Signed-off-by: Hongxia Yang <hongxiay.yang@amd.com>
Co-authored-by: Hongxia Yang <hongxiay.yang@amd.com>
```
  4a00a511
13 Feb, 2026 2 commits

[Bugfix] Replace c10::optional with std::optional in topk kernel (#34467) · bcd65c1f
Pushpinder Singh authored Feb 13, 2026
```
Signed-off-by: Pushpinder Singh <pushpindersingh135@gmail.com>
```
bcd65c1f

[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to... · 59d53066

Wei Zhao authored Feb 13, 2026


[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

59d53066

12 Feb, 2026 2 commits
- small adjustment to wvSplitKrc (#34410) · fac4e969
  Hashem Hashemi authored Feb 12, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
  fac4e969
- [Bugfix] Fix Sparse24 Compressed Tensors models (#33446) · e9cd6911
  Kyle Sayers authored Feb 12, 2026
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  e9cd6911
11 Feb, 2026 4 commits
- [Bugfix][CPU] Fix llama4 inference on CPU (#34321) · 05339a7b
  Li, Jiang authored Feb 11, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  05339a7b
- [CPU] Enable FP16 (Half dtype) support for s390x (#34116) · d1b837f0
  R3hankhan authored Feb 11, 2026
```
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
```
  d1b837f0
- [Kernel] Apply 256bit LDG/STG To Activation Kernels (#33022) · 1485396a
  Дзержи́нский authored Feb 11, 2026
```
Signed-off-by: Dzerzhinsky <256908701+AstroVoyager7@users.noreply.github.com>
Signed-off-by: Дзержи́нский <256908701+AstroVoyager7@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  1485396a
- [Bugfix][DeepSeek-V3.2] fix fp8 kvcache type cast (#33884) · 5ee5c86e
  Kebe authored Feb 11, 2026
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  5ee5c86e
10 Feb, 2026 1 commit

[Perf][Kernel] Add faster topKperRow decode kernel for DeepSeek-V3.2 sparse attention (#33680) · afdce12c

Roberto L. Castro authored Feb 10, 2026

Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

afdce12c

09 Feb, 2026 2 commits
- [Fix] [CPU Backend] : Prepack weights for w8a8 oneDNN matmul (#33901) · caad9f1e
  Nikhil Gupta authored Feb 09, 2026
```
Signed-off-by: nikhil-arm <nikhil.gupta2@arm.com>
```
  caad9f1e
- fix(cpu): fix mla_decode compilation on x86 without AVX512 (#34052) · 5a5c4351
  ihb2032 authored Feb 09, 2026
```
Signed-off-by: ihb2032 <hebome@foxmail.com>
Co-authored-by: root <root@LAPTOP-FKNHV411.localdomain>
```
  5a5c4351
07 Feb, 2026 2 commits
- Perf tuning and expansion of cases covered for wvSplitKrc (#33493) · ed17f54c
  Hashem Hashemi authored Feb 07, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
  ed17f54c
- [Kernel] Add enable_sm120_or_later for SM121 (DGX Spark) CUTLASS support (#33517) · bc32444b
  Vel authored Feb 06, 2026
```
Signed-off-by: code4me2 <velvetmoon222999@gmail.com>
```
  bc32444b
06 Feb, 2026 3 commits
- [Refactor] Remove align block size logic in `moe_permute` (#33449) · 77c09e11
  Wentao Ye authored Feb 06, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  77c09e11
- [cpu][performance] CPU Paged Attention NEON BFMMLA BF16 Implementation (#32263) · 1363e3d6
  Gassan Salama authored Feb 06, 2026
```
Signed-off-by: Gassan <gassan.salama@arm.com>
```
  1363e3d6
- [CPU] Add BF16 Kernel type for s390x (#33788) · ac04dd37
  R3hankhan authored Feb 06, 2026
```
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
```
  ac04dd37
05 Feb, 2026 1 commit
- Adds padding and perf improvements to wvSplitK_fp8 (#33527) · d5c48001
  Hashem Hashemi authored Feb 05, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
  d5c48001