biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
13,454 Commits 2 Branches 140 Tags
a2ef06e1b3a1c0dc4f7bf6587fbdcf1dad287c31
Commit Graph

689 Commits

Author SHA1 Message Date
Gregory Shtrasberg
31aedfe7d6 [Bugfix][ROCm] Fixing the skinny gemm dispatch logic from #32831 (#33366) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2026-01-30 19:05:23 -06:00
Michael Goin
67ebaff528 Refactor NVFP4 Linear utils for ModelOpt and CT (#33201) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-01-30 16:37:42 -08:00
Pavani Majety
c3a9752b0c [Hardware][SM100] Add TRTLLM Kernel for INT4 W4A16 Kernel. (#32437) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
 2026-01-30 10:30:46 -08:00
Yanan Cao
6c1f9e4c18 [Kernel] [Helion] [1/N] Add Helion ConfigManager (#32740) 
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
 2026-01-30 12:19:19 -05:00
Harry Mellor
a11bc12d53 Fix test_moe.py for Transformers v5 (#33413) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-01-30 14:03:25 +00:00
Robert Shaw
af9b69f977 [Quantization][Deprecation] Remove Marlin 24 (#32688) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-01-28 15:54:59 +00:00
Richard Zou
d9aa39a3bb [torch.compile] Speed up MOE handling in forward_context (#33184) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2026-01-27 15:17:54 -08:00
Matthew Bonanni
a608b4c6c2 [5/N][Attention] Finish eliminating vllm/attention folder (#32064) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-27 10:02:51 -05:00
Robert Shaw
5a93b9162b [MoE Refactor] Integrate Naive Prepare Finalize into MK (#32567) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: amirkl94 <203507526+amirkl94@users.noreply.github.com>
 2026-01-27 01:28:02 +00:00
Roberto L. Castro
fcb9df99bd [Perf][Kernel] Optimize FP4 quantization kernels (SM100F) (#32520) 
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
 2026-01-24 18:45:27 -07:00
7. Sun
0ccecf8833 [Tests] Standardize RNG seed utility across test files (#32982) 
Signed-off-by: 7. Sun <jhao.sun@gmail.com>
 2026-01-24 06:47:14 +00:00
Michael Goin
4561f13985 [Refactor] Rename gptq_marlin to marlin to match MoE (#32952) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-01-23 16:48:12 -05:00
Matt
305e53ade8 [Hardware][AMD][CI][Bugfix] Fix Kernels Attention Cache test (#32904) 
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
 2026-01-23 16:24:26 +00:00
Fadi Arafeh
aac0b817fa [CPU Backend][BugFix] Fix failing CPU MoE test (#32876) 
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
 2026-01-23 12:06:51 +00:00
Karan Bansal
fa6e599a61 [Bugfix] Fix _CPU_MOE_ACT AssertionError when vLLM config not set (#32777) 
Signed-off-by: Karan Bansal <karanb192@gmail.com>
 2026-01-23 08:22:37 +00:00
Luka Govedič
5e4e0e51f4 [torch.compile] Compile CustomOp.forward_native for SiluAndMul and QuantFP8 to avoid raw torch ops inside opaque custom ops (#32806) 
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-01-22 19:52:26 -08:00
bnellnm
dc917cceb8 [MoE Refactor] Move select_experts from FusedMoEQuantMethod -> FusedMoE (#31996) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2026-01-22 18:21:35 -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
Eldar Kurtić
44f08af3a7 Add llmcompressor fp8 kv-cache quant (per-tensor and per-attn_head) (#30141) 
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
Signed-off-by: eldarkurtic <8884008+eldarkurtic@users.noreply.github.com>
 2026-01-22 13:29:57 -07:00
Richard Zou
654a71fc3c [torch.compile] Improve Cold Start for MoEs (#32805) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2026-01-22 10:44:40 -05:00
Or Ozeri
421012b63a OffloadingConnector: Support kernel_block_size != block_size (#30692) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2026-01-22 12:30:04 +00:00
Alex Sun
49a1262267 [AMD][ROCm] MoRI EP: a high-performance all2all backend (#28664) 
Signed-off-by: Alex Sun <alex.s@amd.com>
 2026-01-22 16:33:18 +08:00
Xin Yang
63227accf5 [Kernel] Add topk_sigmoid kernel (#31246) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
 2026-01-21 22:49:51 +00:00
elvischenv
808d6fd7b9 Bump Flashinfer to v0.6.1 (#30993) 
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
 2026-01-21 08:49:50 -08:00
whx
1861ae8aae [PluggableLayer][1/N] Define PluggableLayer (Fix ci) (#32744) 
Signed-off-by: whx-sjtu <2952154980@qq.com>
 2026-01-21 11:38:04 -05:00
Robert Shaw
85f55c943c [Quantization][Deprecation] Deprecate HQQ (#32681) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-01-21 09:32:40 -05:00
Robert Shaw
42135d6898 [MoE Refactor] Oracle Select FP8+NVFP4 Kernels In Priority (#32414) 2026-01-21 08:22:33 -05:00
Lucas Wilkinson
b4f64e5b02 Update FlashMLA (#32491) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-21 13:03:37 +08:00
linhaifeng
7901109ea5 [Bugfix] Fix Off-by-one error in _num_tokens_to_min_blocks calculation (#32603) 
Signed-off-by: linhaifeng <1371675203@qq.com>
 2026-01-20 11:13:39 -05:00
vllmellm
148117ea2e [Refactor] Make FP8 Linear Ops use kernel abstraction (#27814) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-01-20 14:48:20 +08:00
Yanan Cao
9d1e611f0e [CI] Add Helion as an optional dependency (#32482) 
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
 2026-01-19 19:09:56 +00:00
Matt
11bbf86f6a [CI][Hardware][AMD] Fix test_rotary_embedding_mla_cache_fused (#32408) 
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
 2026-01-19 08:25:47 +00:00
bnellnm
327a02d8db [MoE Refactor] Separate Router into OO Classes (#30623) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2026-01-18 11:40:49 -05:00
Robert Shaw
4a6af8813f [MoE Refactor] Move Test Impl into Test Dirs (#32129) 
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
 2026-01-18 12:16:59 +08:00
Hashem Hashemi
7a1030431a Atomics Reduce Counting Optimization for SplitK Skinny GEMMs. (#29843) 
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
 2026-01-16 11:45:04 -06:00
rasmith
6ca4f400d8 [CI][AMD] Skip test_permute_cols since the kernel is not used and not built for ROCm (#32444) 
Signed-off-by: Randall Smith <ransmith@amd.com>
 2026-01-16 16:22:53 +08:00
TomerBN-Nvidia
c277fbdf31 [Feat] Support non-gated MoE with Marlin, NVFP4 CUTLASS, FP8, INT8, compressed-tensors (#32257) 
Signed-off-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@ipp1-1429.ipp1a1.colossus.nvidia.com>
 2026-01-15 16:15:05 -08:00
rasmith
8853a50af2 [CI][BugFix][AMD][FP8] Fix test_rms_norm so it runs correctly on ROCm (#32372) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2026-01-15 19:05:54 +08:00
rasmith
3c2685645e [CI][AMD][Quantization][BugFix] Fix fp8 max in quant_utils.py and update test_fp8_quant.::test_static_fp8_quant_group_2d to use correct fp8 dtype and adjust atol/rtol (#32201) 
Signed-off-by: Randall Smith <ransmith@amd.com>
 2026-01-15 05:04:34 +00:00
Hongxia Yang
048bb59728 AMD CI Test - unskip moe_sum test and moe_align_block_size tests (#32039) 
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
 2026-01-13 23:25:10 -08:00
Roberto L. Castro
8ef50d9a6b [Kernel][Performance] Enable smaller Scaling Factor tiling for NVFP4 small-batch decoding (#30885) 
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
 2026-01-13 15:22:53 -08:00
Rabi Mishra
69f8a0ea37 fix(rocm): Use refresh_env_variables() for rocm_aiter_ops in test_moe (#31711) 
Signed-off-by: rabi <ramishra@redhat.com>
 2026-01-13 19:11:54 +00:00
danielafrimi
3f72639d36 [FIX] Add NO_MUL activation support for modular kernel path (#31528) 
Signed-off-by: dafrimi <dafrimi@nvidia.com>
Signed-off-by: <>
Co-authored-by: root <root@gpu-267.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: root <root@gpu-537.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: root <root@pool0-01777.cm.cluster>
 2026-01-12 11:55:49 -05:00
Jiangyun Zhu
3df619ac94 [CI] fix test_concat_and_cache_mla_rope_fused (#32117) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2026-01-11 15:11:11 +00:00
shyeh25
1c46dea001 Revert "[Kernels][FI] Skip trtllm attention when num_kv_heads=1 (#308… (#31617) 
Signed-off-by: shyeh25 <206795756+shyeh25@users.noreply.github.com>
 2026-01-10 12:39:59 -08:00
PatrykSaffer
80fead8bf6 Fuse RoPE and MLA KV-cache write (#25774) 
Signed-off-by: Patryk Saffer <patryk.saffer99@gmail.com>
Signed-off-by: PatrykSaffer <patryk.saffer@mistral.ai>
Co-authored-by: Patryk Saffer <patryk.saffer99@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-01-09 19:18:37 -08:00
Matthew Bonanni
2612ba9285 [1/N][Attention] Restructure attention: move files (#31916) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-09 13:10:24 -08:00
Lucas Wilkinson
0a0aa07747 [Quant] Make static quant support all group shapes (#30833) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-09 12:49:27 -08:00
Runkai Tao
a4d5d663e2 Add unpermute-aware fused MoE path and small-batch fallback (#29354) 
Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2026-01-09 12:58:39 -07:00
vllmellm
1a19e9cd87 [Bugfix][ROCm]Fix Qwen3-Next-80B-A3B-Thinking inference and optimize non-standard block size (544) support under rocm_atten (#31380) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-01-09 19:28:02 +08:00