jiahanc
34553b9d27
[Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next ( #27492 )
...
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
2025-11-10 12:34:57 -05:00
Ilya Markov
e50c454672
[BugFix] Support EP/DP + EPLB with MTP ( #25311 )
...
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2025-11-05 15:22:17 +00:00
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
Jee Jee Li
f0a30a067b
[Bugfix] Fix qwen-moe packed_modules_mapping ( #26634 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-10-11 15:21:33 +00:00
Rahul Tuli
d2a71530c1
Add EAGLE-3 Speculative Decoding Support for Qwen3 MoE ( #26485 )
...
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
2025-10-11 10:14:41 +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
Roger Wang
6144754014
[Bugfix] Fix Qwen3-VL regression from #24982 ( #25814 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-09-28 03:21:09 +00:00
Tyler Michael Smith
a5354b3ed2
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models ( #24982 )
...
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
2025-09-27 14:22:28 +00:00
Isotr0py
d4d9899860
[Quantization] Add field to skip unquantized modules for GPTQ config ( #25455 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-26 15:47:41 +00:00
Woosuk Kwon
1c3ffdbecc
[V0 Deprecation] Remove V0 sampling metadata ( #25345 )
...
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
2025-09-21 10:37:11 -07:00
bnellnm
5963b98b46
[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses ( #22537 )
...
Signed-off-by: Bill Nell <bnell@redhat.com>
2025-09-17 17:43:31 -06:00
whx
4a9375fe9d
[Model] Pass param prefix to LLMHead ( #24862 )
...
Signed-off-by: whx-sjtu <2952154980@qq.com>
2025-09-17 16:01:27 +08:00
Roger Wang
0f7acdd73c
[Model] Support Qwen3-VL Model Series ( #24727 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Huang Jie <92386084+JJJYmmm@users.noreply.github.com>
Co-authored-by: 松灵 <26085463+wulipc@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-17 05:01:04 +00:00
Wentao Ye
3beadc2f25
[Compilation Bug] Fix Inductor Graph Output with Shape Issue ( #24772 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-09-12 21:23:05 +00:00
JartX
183a70967a
[BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and AutoRound-GPTQ) ( #23994 )
...
Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-01 03:33:40 +00:00
Lukas Geiger
de533ab2a1
[Models] Improve iteration over layers ( #19497 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-08-29 09:26:34 +08:00
Isotr0py
a9082a4d14
[Bugfix] Fix Qwen3 MoE GPTQ inference ( #23490 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-08-25 06:40:20 -07:00
rongfu.leng
4fbda0b20c
[Feature] use --eplb_config to set eplb param ( #20562 )
...
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-20 14:07:28 -07:00
yiz-liu
4f510bc2a1
[Model] Removes redundant all-reduce operation in Qwen3MoeSparseMoeBlock ( #23169 )
...
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
2025-08-19 16:18:41 +00:00
Gh0u1L5
b159c0a67a
Fix GGUF loader for Qwen3 MoE. ( #22785 )
...
Signed-off-by: Gh0u1L5 <Gh0u1L5@outlook.com>
2025-08-13 06:08:23 -07:00
Andy Chen
9b94d6ec8f
Enable 4bit bnb prequant MOE ( #21548 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-08-11 19:02:14 -07:00
JartX
1e55dfa7e5
[BUGFIX] KeyError 'layers.14.mlp.gate.g_idx' for Qwen3-MoE with GPTQ on ROCm ( #22017 )
2025-08-11 00:13:30 -07:00
Cyrus Leung
65552b476b
[Misc] Use config definitions from Transformers library ( #21913 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-08 23:10:51 -07:00
Zhiyu
d57dc2364e
Add ModelOpt Qwen3 nvfp4 support ( #20101 )
...
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
2025-08-07 19:18:19 -07:00
Tao He
7377131a2c
[Qwen3] Enable dual-chunk-attention support for Qwen3 models. ( #21924 )
...
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
2025-08-06 19:58:08 -07:00
aladerran
d979dd6beb
[Feature][EPLB] Add eplb support for Qwen3 ( #20815 )
...
Signed-off-by: aladerran <aladerran@gmail.com>
2025-07-30 06:27:57 -07:00
Jee Jee Li
a3a6c695f4
[Misc] Qwen MoE model supports LoRA ( #20932 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-17 18:32:52 +00:00
Jee Jee Li
a99b9f7dee
[Quantization] add BNB for MixtralForCausalLM ( #20893 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-14 07:34:34 +00:00
Jee Jee Li
8020e98c9f
[Quantization][1/N] MoE support BNB-Inflight Quantization ( #20061 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-11 08:01:13 +00:00
bnellnm
78fe77534b
[Kernel] Enable fp8 support for pplx and BatchedTritonExperts. ( #18864 )
...
Signed-off-by: Bill Nell <bnell@redhat.com>
2025-07-03 14:55:40 -07:00
noiji
f5dfa07531
[Bugfix] Skip loading extra parameters for modelopt Qwen3 MoE model ( #19598 )
...
Signed-off-by: noiji <>
2025-06-30 18:21:56 +09:00
Xerxes
e41bf15cd0
[Chore]: qwen3-moe-type-hints-mistake ( #19860 )
...
Co-authored-by: xinnan.hou <hxn02029096@alibaba-inc.com>
2025-06-19 21:43:07 -07:00
Simon Mo
02f0c7b220
[Misc] Add SPDX-FileCopyrightText ( #19100 )
...
Signed-off-by: simon-mo <simon.mo@hey.com>
2025-06-03 11:20:17 -07:00
Isotr0py
f07a673eb2
[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name ( #18358 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-05-19 20:20:12 -07:00
Harry Mellor
26d0419309
Update deprecated type hinting in models ( #18132 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-05-14 22:06:50 -07:00
bnellnm
f9c069c85e
Modularize fused experts and integrate PPLX kernels ( #15956 )
2025-05-14 13:11:54 -07:00
Jee Jee Li
63dc3426e0
[Model] Add packed_modules_mapping for Qwen3-MOE ( #18118 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-05-14 02:13:19 -07:00
Wanrui Dai
f80ae5bdcf
[Kernel] Use fused rmsnorm for some models like qwen3 series ( #17735 )
...
Signed-off-by: evian <eviantai@u.nus.edu>
Co-authored-by: evian <eviantai@u.nus.edu>
2025-05-06 23:10:02 -07:00
Aaron Pham
da4e7687b5
[Fix] Support passing args to logger ( #17425 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2025-04-30 08:06:58 -07:00
Woosuk Kwon
b411418ff0
[Chore] Remove Sampler from Model Code ( #17084 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-24 02:49:33 -07:00
rongfu.leng
5a1e1c8353
[Model] use AutoWeightsLoader for phimoe,qwen2_moe,qwen3_moe ( #16203 )
...
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
2025-04-08 04:05:47 -07:00
YamPengLi
7699258ef0
[Model] Add Qwen3 and Qwen3MoE ( #15289 )
...
Signed-off-by: YamPengLi <yampayne.lyp@alibaba-inc.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-04-07 04:06:41 -07:00
