Commits · 7e08c22b8cb65a1bea6b4bf9c52ed6e71d4acc47 · OpenDAS / vllm_cscc

28 Feb, 2026 1 commit
- [Feat] Add CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#35271) · 7e08c22b
  Chauncey authored Feb 28, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  7e08c22b
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
06 Feb, 2026 2 commits
- [Log] Optimize duplicate startup log (#33944) · 67a746e8
  Wentao Ye authored Feb 06, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  67a746e8
- [Perf] Disable clean_logits in deepgemm fp8_mqa_logits kernel (#33568) · 79028d43
  Xin Yang authored Feb 05, 2026
  
  79028d43
22 Jan, 2026 1 commit
- [Perf] Create TMA-aligned input scale tensor for DeepGemm on Hopper (#32619) · d08b356e
  Xin Yang authored Jan 22, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  d08b356e
20 Jan, 2026 1 commit
- [Bugfix] Fix the fp8_mqa_logits dim mismatch (#32652) · c4e5bdf6
  Chauncey authored Jan 20, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  c4e5bdf6
07 Jan, 2026 1 commit

[Bugfix][Hardware][AMD] Consolidate FP8 min/max values helper function (#31106) · 4614c5a5

Kevin McKay authored Jan 07, 2026


Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Signed-off-by: Kevin McKay <kevin@example.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

4614c5a5

22 Dec, 2025 1 commit
- [Misc] Fix quantization-related typos (#31116) · ec58c10c
  Kevin McKay authored Dec 21, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  ec58c10c
19 Dec, 2025 1 commit
- [Refactor] Refactor for `DeepGemmQuantScaleFMT` using cache (#30898) · 3bd8335b
  Wentao Ye authored Dec 19, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  3bd8335b
14 Dec, 2025 1 commit
- [Bugfix] Fix fusion for VL models (#30244) · 994acec0
  ElizaWszola authored Dec 14, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
  994acec0
13 Dec, 2025 1 commit

[Feature] Add SM103 (Blackwell Ultra) Support to vLLM (#30484) · 4fa7ce46

Roberto L. Castro authored Dec 13, 2025

Signed-off-by: LopezCastroRoberto <robertol.c510@gmail.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

4fa7ce46

09 Dec, 2025 1 commit

[Bugfix] Fix DeepGEMM after #29546 (#30267) · ae339b1a

Zhewen Li authored Dec 08, 2025


Signed-off-by: zhewenli <zhewenli@meta.com>
Signed-off-by: Zhewen Li <zhewenli@meta.com>

ae339b1a

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

20 Nov, 2025 1 commit
- [ROCm] Add AMD GPU support on Deepseek v3.2 and SparseMLA (#26670) · 06c20c99
  Pleaplusone authored Nov 20, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
```
  06c20c99
19 Nov, 2025 1 commit

[Performance] Reduce DeepGEMM N dim restriction from 128 to 64 multiplier (#28687) · 3aaa94ac

Alexander Matveev authored Nov 19, 2025


Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

3aaa94ac

13 Nov, 2025 1 commit

[Performance][B200] silu_mul_quant: pack scales in int32 (#28358) · fe1cd770

Varun Sundar Rabindranath authored Nov 13, 2025


Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>

fe1cd770

12 Nov, 2025 1 commit

[Performance][B200] Fix deepgemm prologue (#27897) · 74a9a9fa

Varun Sundar Rabindranath authored Nov 12, 2025


Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>

74a9a9fa

26 Oct, 2025 1 commit

[Chore]:Extract math and argparse utilities to separate modules (#27188) · 71b1c8b6

Yeshwanth N authored Oct 26, 2025


Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>

71b1c8b6

22 Oct, 2025 1 commit

[Chore] Separate out optional dependency checks from vllm.utils (#27207) · 3ae082c3

dongbo910220 authored Oct 22, 2025

Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

3ae082c3

17 Oct, 2025 1 commit
- [Docs] Replace `rst` style double-backtick with `md` single-backtick (#27091) · 6c9fdbf7
  Harry Mellor authored Oct 17, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6c9fdbf7
16 Oct, 2025 1 commit

[Feature] Migrate DeepGEMM API from `get_m_alignment_for_contiguous_layout` to... · b3dda72c

Wentao Ye authored Oct 16, 2025


[Feature] Migrate DeepGEMM API from `get_m_alignment_for_contiguous_layout` to `get_mk_alignment_for_contiguous_layout` (#26935)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

b3dda72c

12 Oct, 2025 1 commit
- Update `Optional[x]` -> `x | None` and `Union[x, y]` to `x | y` (#26633) · 8fcaaf6a
  Harry Mellor authored Oct 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8fcaaf6a
08 Oct, 2025 1 commit

[Feature] Enable E8M0 by Default on Hopper for DeepGEMM, 5% E2E throughput improvement (#26197) · f8607863

Wentao Ye authored Oct 08, 2025

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

f8607863

05 Oct, 2025 2 commits
- Fix per file ruff ignores related to typing (#26254) · 1c0c6820
  Harry Mellor authored Oct 05, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  1c0c6820
- Convert formatting to use `ruff` instead of `yapf` + `isort` (#26247) · d6953beb
  Harry Mellor authored Oct 05, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d6953beb
03 Oct, 2025 1 commit
- [Log] Optimize DeepGEMM Missing Log (#26106) · 36ce76c6
  Wentao Ye authored Oct 02, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  36ce76c6
02 Oct, 2025 1 commit

[Perf] Fix and reapply move apply w8a8 block fp8 linear to class (#25696) · 502640c3

ElizaWszola authored Oct 02, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

502640c3

30 Sep, 2025 2 commits

[Bugfix] Fix accuracy issue of TRTLLM FP8 MOE and improve logging (#25895) · ef283548
Pavani Majety authored Sep 30, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
ef283548

[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896) · fa7e254a

Yongye Zhu authored Sep 30, 2025


Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>

fa7e254a

25 Sep, 2025 1 commit
- Revert "[Performance] Move apply_w8a8_block_fp8_linear to an op class… (#25607) · 1260180c
  Tyler Michael Smith authored Sep 25, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  1260180c
24 Sep, 2025 1 commit
- [Refactor] Use DeepGEMM Col Major TMA Aligned Tensor (#25517) · 1f291412
  Wentao Ye authored Sep 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  1f291412
23 Sep, 2025 2 commits

[Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666) · 63400259

ElizaWszola authored Sep 23, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

63400259

[Perf] Apply torch.compile for `per_block_cast_to_fp8` (#24611) · 9949aa2e
Wentao Ye authored Sep 22, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
9949aa2e

16 Sep, 2025 1 commit
- [Deprecation] Remove DeepGEMM Old Symbol Wrapper (#24902) · de2cc3d8
  Wentao Ye authored Sep 15, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  de2cc3d8
28 Aug, 2025 1 commit
- [Log] Use Debug Once for DeepGEMM E8M0 When not Enabled (#23858) · d3d2aad5
  Wentao Ye authored Aug 28, 2025
  
  d3d2aad5
27 Aug, 2025 1 commit

[Feature] Add Hopper DeepGEMM E8M0 for DeepSeekV3.1 scale_fmt (#23666) · 3af47c3c

Wentao Ye authored Aug 27, 2025


Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

3af47c3c

26 Aug, 2025 1 commit
- [Bug] Fix DeepGEMM Env Control (#23591) · 56dcf4e7
  Wentao Ye authored Aug 25, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  56dcf4e7
22 Aug, 2025 1 commit
- [Feature] Enable DeepGEMM Linear on B200; 1.5% E2E throughput improvement (#23351) · 394591e3
  Wentao Ye authored Aug 22, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  394591e3
11 Aug, 2025 1 commit
- [Feature] Add `VLLM_USE_DEEP_GEMM_E8M0` Env to Control E8M0 Scale (#21968) · f7dcce7a
  Wentao Ye authored Aug 11, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  f7dcce7a
09 Aug, 2025 1 commit
- [Log] Add Warning for Deprecation of DeepGEMM old version (#22194) · 3157aebb
  Wentao Ye authored Aug 09, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  3157aebb