 Chauncey
|
7e08c22b8c
|
[Feat] Add CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#35271)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-02-28 10:12:00 +00:00 |
|
|
ElizaWszolaandLuka Govedič
|
a88b3be7c4
|
[Bugfix] Fix quant RMS norm fusion for quantization with TMA-aligned scales (#33255)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2026-02-17 23:35:04 -08:00 |
|
|
Wentao Ye
|
67a746e87f
|
[Log] Optimize duplicate startup log (#33944)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-02-06 17:49:56 +00:00 |
|
|
Xin Yang
|
79028d4388
|
[Perf] Disable clean_logits in deepgemm fp8_mqa_logits kernel (#33568)
|
2026-02-05 20:34:00 -05:00 |
|
|
Xin Yang
|
d08b356ee0
|
[Perf] Create TMA-aligned input scale tensor for DeepGemm on Hopper (#32619)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-01-22 15:47:04 -05:00 |
|
|
Chauncey
|
c4e5bdf61b
|
[Bugfix] Fix the fp8_mqa_logits dim mismatch (#32652)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-01-20 18:48:07 +08:00 |
|
|
Kevin McKayandClaude Sonnet 4.5
|
4614c5a539
|
[Bugfix][Hardware][AMD] Consolidate FP8 min/max values helper function (#31106)
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>
|
2026-01-07 06:55:03 +00:00 |
|
|
Kevin McKay
|
ec58c10ce1
|
[Misc] Fix quantization-related typos (#31116)
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
|
2025-12-21 21:13:48 -08:00 |
|
|
Wentao Ye
|
3bd8335bd0
|
[Refactor] Refactor for DeepGemmQuantScaleFMT using cache (#30898)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-12-19 13:50:39 -07:00 |
|
|
ElizaWszola
|
994acec0cc
|
[Bugfix] Fix fusion for VL models (#30244)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
|
2025-12-14 21:22:37 +08:00 |
|
|
Roberto L. Castroandyoukaichao
|
4fa7ce46f3
|
[Feature] Add SM103 (Blackwell Ultra) Support to vLLM (#30484)
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>
|
2025-12-12 19:34:23 -08:00 |
|
|
Zhewen Li
|
ae339b1a67
|
[Bugfix] Fix DeepGEMM after #29546 (#30267)
Signed-off-by: zhewenli <zhewenli@meta.com>
Signed-off-by: Zhewen Li <zhewenli@meta.com>
|
2025-12-09 01:05:27 +00:00 |
|
|
ElizaWszolaandyewentao256
|
af0444bf40
|
[Performance] Fused blockwise quant RMS norm (#27883)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
|
2025-12-07 16:38:04 +00:00 |
|
|
Pleaplusone
|
06c20c9904
|
[ROCm] Add AMD GPU support on Deepseek v3.2 and SparseMLA (#26670)
Signed-off-by: ganyi <ygan@amd.com>
|
2025-11-20 02:54:01 -08:00 |
|
|
Alexander Matveevandmgoin
|
3aaa94ac99
|
[Performance] Reduce DeepGEMM N dim restriction from 128 to 64 multiplier (#28687)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-11-19 15:47:13 -08:00 |
|
|
Varun Sundar RabindranathandVarun Sundar Rabindranath
|
fe1cd7704d
|
[Performance][B200] silu_mul_quant: pack scales in int32 (#28358)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
|
2025-11-13 10:16:55 -08:00 |
|
|
Varun Sundar RabindranathandVarun Sundar Rabindranath
|
74a9a9faad
|
[Performance][B200] Fix deepgemm prologue (#27897)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
|
2025-11-12 13:13:03 -08:00 |
|
|
Yeshwanth N
|
71b1c8b667
|
[Chore]:Extract math and argparse utilities to separate modules (#27188)
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>
|
2025-10-26 04:03:32 -07:00 |
|
|
|
3ae082c373
|
[Chore] Separate out optional dependency checks from vllm.utils (#27207)
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>
|
2025-10-22 10:44:21 -04:00 |
|
|
Harry Mellor
|
6c9fdbf725
|
[Docs] Replace rst style double-backtick with md single-backtick (#27091)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-17 02:47:34 -07:00 |
|
|
Wentao Yeandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
b3dda72c23
|
[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>
|
2025-10-16 16:46:48 -04:00 |
|
|
Harry Mellor
|
8fcaaf6a16
|
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-12 09:51:31 -07:00 |
|
|
Wentao Yeandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
f8607863d8
|
[Feature] Enable E8M0 by Default on Hopper for DeepGEMM, 5% E2E throughput improvement (#26197)
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>
|
2025-10-08 15:33:56 +08:00 |
|
|
Harry Mellor
|
1c0c68202c
|
Fix per file ruff ignores related to typing (#26254)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-05 16:37:55 +00:00 |
|
|
Harry Mellor
|
d6953beb91
|
Convert formatting to use ruff instead of yapf + isort (#26247)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-05 07:06:22 -07:00 |
|
|
Wentao Ye
|
36ce76c632
|
[Log] Optimize DeepGEMM Missing Log (#26106)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-10-02 20:02:26 -06:00 |
|
|
|
502640c3f9
|
[Perf] Fix and reapply move apply w8a8 block fp8 linear to class (#25696)
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>
|
2025-10-02 19:35:13 +00:00 |
|
|
Pavani Majety
|
ef283548f7
|
[Bugfix] Fix accuracy issue of TRTLLM FP8 MOE and improve logging (#25895)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
|
2025-09-30 10:51:31 -04:00 |
|
|
+6
|
fa7e254a7f
|
[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896)
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>
|
2025-09-30 17:14:41 +08:00 |
|
|
Tyler Michael Smith
|
1260180c67
|
Revert "[Performance] Move apply_w8a8_block_fp8_linear to an op class… (#25607)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2025-09-25 08:05:21 +00:00 |
|
|
Wentao Ye
|
1f29141258
|
[Refactor] Use DeepGEMM Col Major TMA Aligned Tensor (#25517)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-09-24 18:52:36 -04:00 |
|
|
|
63400259d0
|
[Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666)
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>
|
2025-09-23 12:03:10 -07:00 |
|
|
Wentao Ye
|
9949aa2ef1
|
[Perf] Apply torch.compile for per_block_cast_to_fp8 (#24611)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-09-22 19:42:45 -06:00 |
|
|
Wentao Ye
|
de2cc3d867
|
[Deprecation] Remove DeepGEMM Old Symbol Wrapper (#24902)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-09-15 20:03:29 -06:00 |
|
|
Wentao Ye
|
d3d2aad5a2
|
[Log] Use Debug Once for DeepGEMM E8M0 When not Enabled (#23858)
|
2025-08-28 22:18:10 +00:00 |
|
|
Wentao Yeandyoukaichao
|
3af47c3cc6
|
[Feature] Add Hopper DeepGEMM E8M0 for DeepSeekV3.1 scale_fmt (#23666)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
|
2025-08-27 14:09:08 +00:00 |
|
|
Wentao Ye
|
56dcf4e7e9
|
[Bug] Fix DeepGEMM Env Control (#23591)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-25 18:41:21 -07:00 |
|
|
Wentao Ye
|
394591e343
|
[Feature] Enable DeepGEMM Linear on B200; 1.5% E2E throughput improvement (#23351)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-21 21:01:08 -07:00 |
|
|
Wentao Ye
|
f7dcce7a4a
|
[Feature] Add VLLM_USE_DEEP_GEMM_E8M0 Env to Control E8M0 Scale (#21968)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-11 09:39:08 -07:00 |
|
|
Wentao Ye
|
3157aebb63
|
[Log] Add Warning for Deprecation of DeepGEMM old version (#22194)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-08 23:07:48 -07:00 |
|
|
Wentao Ye
|
6e8d8c4afb
|
[Test] Add Unit Test for Batched DeepGEMM (#21559)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-02 10:45:46 +08:00 |
|
|
Varun Sundar RabindranathandVarun Sundar Rabindranath
|
a65f46be5e
|
[Misc] DeepGemmExperts : Avoid JIT generation in the hot-path (#21955)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
|
2025-08-01 19:42:03 -07:00 |
|
|
Wentao Ye
|
3700642013
|
[Refactor] Remove Duplicate per_block_cast_to_fp8, Remove Dependencies of DeepGEMM (#21787)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-01 01:13:27 +00:00 |
|
|
Matthew Bonanniandmgoin
|
e360316ab9
|
Add DeepGEMM to Dockerfile in vllm-base image (#21533)
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-07-31 18:01:55 -07:00 |
|
|
Clayton Colemanandmgoin
|
c6f36cfa26
|
[Bugfix] DeepGEMM is not enabled on B200 due to _lazy_init() (#21472)
Signed-off-by: Clayton Coleman <smarterclayton@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-07-28 20:51:22 +00:00 |
|
|
Wentao Ye
|
e69a92a1ce
|
[Bug] DeepGemm: Fix Cuda Init Error (#21312)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-21 23:36:18 -07:00 |
|
|
Wentao Ye
|
37bd8d6e4c
|
[Bug] DeepGemm: Fix TypeError: per_block_cast_to_fp8() missing 1 required positional argument: 'use_ue8m0' for SM100 (#21187)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-18 23:25:22 -07:00 |
|
|
Wentao Ye
|
42d440c22b
|
[Perf] Use Triton instead of Torch for DeepGEMM Per Token Group Quant (#20841)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-12 19:38:45 -07:00 |
|
|
Wentao Ye
|
e2de455c34
|
[Feature] Integrate SM100 DeepGEMM support (#20087)
|
2025-07-10 20:18:05 -07:00 |
|