xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-07 11:27:08 +08:00
Code Issues Packages Projects Releases Wiki Activity
10,933 Commits 155 Branches 89 Tags
Commit Graph

1413 Commits

Author SHA1 Message Date
vllmellm
fb72ec8218 add missing kernels for cuda dispatch 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-04 12:23:38 +00:00
vllmellm
f10171cb3d correct minimum capability req for channelwise torch 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-04 12:22:49 +00:00
vllmellm
a76f7bb90c rename flash_infer.py to flashinfer.py 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-04 12:13:02 +00:00
vllmellm
f5e6cd9695 prefer QuantKey over ScaledMMLinearQuantStrategy 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-04 12:11:13 +00:00
vllmellm
a8010c7b1c flash_infer missing out dtype bug fix 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-03 08:02:45 +00:00
vllmellm
7794009661 add missing arg 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-03 07:09:52 +00:00
vllmellm
b13c4bb25c remove FP8LinearOps 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-01 16:30:32 +00:00
vllmellm
52ff537459 update modelopt path 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-01 16:28:18 +00:00
vllmellm
dd5a70ec71 update unit tests to use ScaledMMLinearKernels 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-01 16:28:03 +00:00
vllmellm
4ce0ba2df4 format 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-01 10:01:13 +00:00
vllmellm
8e8218ebac Merge remote-tracking branch 'origin/main' into refactor-fp8-linear 2025-11-01 09:59:43 +00:00
vllmellm
d92c23b446 fix types; reduce boilerplate for int8 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-11-01 09:59:00 +00:00
Jee Jee Li
3a5de7d2d6
[Bugfix] Fix KDA output (#27905) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-01 11:54:36 +08:00
Jee Jee Li
bc4486d609
[Kernel] Enable FusedMoEModularKernel support bias (#27754) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-01 02:05:12 +00:00
Shu Wang
fc16f1c477
Flashinfer_CUTLASS_MOE fuses quantization for TP (#27223) 
Signed-off-by: Shu Wang. <shuw@nvidia.com>
 2025-10-31 17:54:29 +00:00
vllmellm
e845035f4c bug fix 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-31 16:38:26 +00:00
vllmellm
5fbe76bc0a format; update fbgemm path 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-31 15:08:19 +00:00
vllmellm
1f65cd56e5 revert input scale upper bounds 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-31 15:06:51 +00:00
vllmellm
7d361487f7 update ptpc path; bug fixes 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-31 14:52:51 +00:00
vllmellm
dd001064c0 reduce kernel init boilerplate 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-31 14:21:49 +00:00
vllmellm
423e2a625e reduce logging boilerplate; update fp8 path 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-31 14:07:09 +00:00
Jiangyun Zhu
3857eb8725
[Perf] Decouple torch op from GDA to leverage torch.compile (#27871) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-10-31 21:35:52 +08:00
vllmellm
38825fce0f
Merge branch 'main' into refactor-fp8-linear 2025-10-31 15:58:25 +08:00
Paul Zhang
e7acb20076
[Feature] Batch invariant torch.compile (#27660) 
Signed-off-by: PaulZhang12 <paulzhan@fb.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-10-30 13:11:29 -07:00
Roger Meier
2918c1b49c
[Model] Use the same fused_moe configs for all H200 devices (#23642) 
Signed-off-by: Roger Meier <r.meier@siemens.com>
 2025-10-30 17:36:56 +00:00
Li, Jiang
eebf00cb0c
[Bugfix][CPU] Fix MRoPE dispatch on the CPU backend (#27800) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-10-30 15:12:05 +00:00
vllmellm
c089ea5753 update quark fp8 path; format 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-30 14:24:19 +00:00
Zhiyuan Li
4e68cc9b6a
[Model] Introduce Kimi Linear to vLLM (#27809) 
Signed-off-by: lizhiyuan <lizhiyuan@moonshot.cn>
Signed-off-by: Zhiyuan Li <uniartisan2017@gmail.com>
 2025-10-30 21:02:27 +08:00
vllmellm
c05027f67a clean up; fix quark path 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-30 12:27:04 +00:00
wang.yuqi
4464723f22
[Frontend][Doc][5/N] Improve all pooling task | Polish encode (pooling) api & Document. (#25524) 
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-10-30 12:13:05 +00:00
vllmellm
e54e572085 fix int8 path 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-30 08:04:24 +00:00
Bram Wasti
ded8ada86a
Add more dims for batch invariant shims (#27489) 
Signed-off-by: Bram Wasti <bwasti@meta.com>
Signed-off-by: Bram Wasti <bwasti@fb.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-10-30 05:28:45 +00:00
Yan Ma
b798e39f93
[XPU][bugfix] fix rope for llama4 and deepseek (#25145) 
Signed-off-by: Yan Ma <yan.ma@intel.com>
 2025-10-30 09:43:13 +08:00
Wentao Ye
b5d90f7400
[Bug] Fix DBO IMA issue for DeepEPHT (#27666) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-29 16:28:27 -04:00
Wentao Ye
fcb1d570bb
[Bug] Fix DeepEP low latency assert self.batched_router_logits.size(-1) == full_router_logits.size(-1) Bug (#27682) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-29 14:50:39 -04:00
Roger Young
d6704dd099
Fix MiniMax-M2 rmsnorm precision and remove useless code (#27627) 
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
 2025-10-29 21:01:05 +08:00
Zhewen Li
8b62495076
[Bugfix] Fix non-contiguous tensor error in rocm_unquantized_gemm_impl (#27605) 
Signed-off-by: zhewenli <zhewenli@meta.com>
 2025-10-29 00:00:15 -07:00
Wentao Ye
6afc28a9ba
[Test] Batch Invariant: Unit test using parameterized backend (#27478) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-28 13:51:35 -07:00
vllmellm
974e6820ce first try 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-10-28 16:26:51 +00:00
Zhiyuan Li
e88bdd60d9
[FLA] Introduce Kimi Delta Attention(KDA) to VLLM (#27654) 
Signed-off-by: lizhiyuan <lizhiyuan@moonshot.cn>
 2025-10-28 22:56:28 +08:00
Wentao Ye
0484b64248
[Bug] Fix shape issue for eplb expert weights (#27589) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-10-28 20:44:05 +08:00
Matthew Bonanni
44b5ce956d
[Bugfix] In LongRoPE, decide short vs long based on max_model_len (#27431) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-10-28 12:00:56 +00:00
Li, Jiang
d34f5fe939
[Bugfix][CPU] Fallback oneDNN linear to torch linear to fix half gemm support on legecy platforms (#27526) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-10-27 23:25:44 -07:00
Eric Yue
bdb01a38fe
[Hardware][AMD][Model] Triton MoE tuning configs for GLM-4.6 for MI300X (#27323) 
Signed-off-by: minatoaquaMK2 <jiacheng.yue@foxmail.com>
 2025-10-27 22:58:06 -07:00
Varun Sundar Rabindranath
5d3be3ba4c
[Bugfix][LoRA][FusedMoE] Select MxFP4 Backend based on LoRA Enablement (#27487) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-10-27 07:32:50 -07:00
Cyrus Leung
7c2bdb83dc
[Misc] Clean up utils (#27552) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-27 09:05:40 +00:00
Danielle Robinson
9932ed6a83
[Kernel] Adding split_K implementation for fused_moe_lora (#27291) 
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Signed-off-by: Danielle Robinson <dcmaddix@gmail.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-10-27 02:05:24 -07:00
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
Varun Sundar Rabindranath
269c4db0a4
[Misc][DP] Guard mxfp4 implementation selection (#27484) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-10-24 23:29:24 +00:00
Wentao Ye
52efc34ebf
[Log] Optimize Startup Log (#26740) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-24 19:27:04 -04:00