 Isotr0py
|
00a4e56d8d
|
[Bugfix] Fix broken deepseek fp8 TP weights loading (#24367)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-06 09:23:12 -07:00 |
|
|
Didier DurandandWentao Ye
|
35bf193864
|
[Doc]: fix typos in Python comments (#24294)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-09-05 19:41:12 -07:00 |
|
|
|
83609ca91d
|
[Doc]: fix typos in Python comments (#24173)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-09-04 08:52:17 -07:00 |
|
|
nvjullinandLuka Govedič
|
37241077d5
|
[Misc] Removed force_fp8_e4m3fnuz from FP8LinearOp (#23725)
Signed-off-by: Julien Lin <jullin@nvidia.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-09-04 09:25:40 -04:00 |
|
|
bnellnm
|
e9b92dcd89
|
[Kernels] Overlap shared experts with send/recv (#23273)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2025-09-03 12:35:18 -04:00 |
|
|
Didier Durand
|
02d411fdb2
|
[Doc]: fix typos in Python comments (#24115)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
|
2025-09-02 21:14:07 -07:00 |
|
|
Didier Durand
|
d7e1e59972
|
[Doc]: fix typos in Python comments (#24093)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
|
2025-09-02 21:05:45 -07:00 |
|
|
co63oc
|
1bd007f234
|
fix some typos (#24071)
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
|
2025-09-02 20:44:50 -07:00 |
|
|
Kyle Sayers
|
1c41310584
|
[Bugfix] Fix transform_config parsing in Compressed Tensors (#23945)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
|
2025-09-02 13:54:10 -04:00 |
|
|
Yan MaandQiming Zhang
|
7be0cb8e9e
|
[XPU][Feature] fp8 online quantization support for XPU (#23148)
Signed-off-by: Yan Ma <yan.ma@intel.com>
Co-authored-by: Qiming Zhang <qiming1.zhang@intel.com>
|
2025-09-02 04:06:53 +00:00 |
|
|
Didier DurandandJee Jee Li
|
0235103cbb
|
[Doc]: fix typos in Python comments (#24042)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-01 19:07:45 -07:00 |
|
|
|
acc1a6e10a
|
Fix the bug related to loading GPTP INT3 weights. (#23328)
Signed-off-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-01 05:39:57 +00:00 |
|
|
JartXandIsotr0py
|
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 |
|
|
|
8fb85b7bb6
|
Add routed_scaling_factor to MoE grouped topk (#23123)
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-08-29 21:36:48 -07:00 |
|
|
Michael Goin
|
b7adf94c4a
|
Tuned H100/H200 triton fp8 block configs for fused_qkv_a_proj (#23939)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-29 10:28:35 -07:00 |
|
|
|
16a45b3a28
|
[NVIDIA] Support SiluMul + NVFP4 quant fusion (#23671)
Signed-off-by: jindih <jindih@nvidia.com>
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: jindih <jindih@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedic <lgovedic@redhat.com>
|
2025-08-28 19:36:50 +00:00 |
|
|
Po-Han Huang (NVIDIA)
|
95089607fa
|
[Model][gpt-oss] Support DP+EP for GPT-OSS with FlashInfer trtllm-gen MoE (#23819)
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
|
2025-08-28 06:56:20 -07:00 |
|
|
Didier Durand
|
d3da2eea54
|
[Doc]: fix typos in Python scripts (#23828)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
|
2025-08-28 05:37:38 -07:00 |
|
|
JartXandMichael Goin
|
3462c1c522
|
[FIXBUG] Add return_success parameter to moe_wna16_weight_loader function (#22797)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-08-28 09:03:22 +00:00 |
|
|
Kyle Sayers
|
22feac8e95
|
[Transform] [Quantization] Add transforms to compressed tensors (#22486)
|
2025-08-28 02:43:48 -04:00 |
|
|
Michael Goin
|
a781e84ec2
|
[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-28 11:12:53 +08:00 |
|
|
Michael Goin
|
f9ca2b40a0
|
[Bugfix] Fix Marlin NVFP4 for modelopt (#23659)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-27 17:48:16 -04:00 |
|
|
Yongye Zhu
|
082cc07ef8
|
DP/EP Support for gpt-oss with deepep-ht comm kernel on SM100 (#23608)
|
2025-08-27 17:33:21 -04:00 |
|
|
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 |
|
|
Dipika Sikka
|
d272415e57
|
[Quantization] Expand compressed-tensors MoE matching logic to support NFP4 + FP8 MoEs (#22674)
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
|
2025-08-27 05:00:21 +00:00 |
|
|
Michael Goin
|
de02b07db4
|
[Bugfix] Lazy import gpt_oss_triton_kernels_moe for mxfp4 (#23678)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-27 09:34:57 +08:00 |
|
|
czhu-cohere
|
2c2b140ae8
|
[quantization] use channel scales for w4a8 + misc fixes (#23570)
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
|
2025-08-26 18:23:23 -07:00 |
|
|
nvjullinandMichael Goin
|
f66673a39d
|
[Kernel] Added flashinfer fp8 per-tensor gemms (#22895)
Signed-off-by: Julien Lin <jullin@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-08-26 06:54:04 -07:00 |
|
|
Michael Goin
|
d52358c1e0
|
[Perf] Remove duplicated NVFP4 blockscales to save memory (#23379)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-26 19:16:33 +08:00 |
|
|
|
ae067888d6
|
Update Flashinfer to 0.2.14.post1 (#23537)
Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: siyuanf <siyuanf@nvidia.com>
Signed-off-by: Weiliang Liu <weiliangl@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-08-25 18:30:44 -07:00 |
|
|
Ming Yang
|
504d914314
|
[Perf] Add Triton config for DeepSeek V3 FP8 EP32 H200 (#23504)
Signed-off-by: Ming Yang <minos.future@gmail.com>
|
2025-08-24 18:06:35 -07:00 |
|
|
czhu-cohere
|
e76e233540
|
[kernel] Support W4A8 on Hopper (#23198)
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
|
2025-08-24 06:18:04 +00:00 |
|
|
Daifeng LiandMichael Goin
|
fa78de9dc3
|
Quantization: support FP4 quantized models on AMD CDNA2/CDNA3 GPUs (#22527)
Signed-off-by: feng <fengli1702@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-08-22 20:53:21 -06:00 |
|
|
elvischenvandLuka Govedič
|
24d0c9e6ed
|
[NVIDIA][torch.compile] Support Flashinfer TRTLLM FP8-q/kv NVFP4-out Attention Kernel (#22703)
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-08-22 22:09:05 +00:00 |
|
|
rasmith
|
cc7ae5e7ca
|
[BugFix][AMD][Quantization] Fix torch.compile issue where wvSplitKQ not being called when it should when using quantized FP8 model (#22281)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
|
2025-08-22 21:47:57 +00:00 |
|
|
Isotr0py
|
4645024d3a
|
[Quantization] Allow GGUF quantization to skip unquantized layer (#23188)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-08-22 13:04:22 -06:00 |
|
|
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 YeandMichael Goin
|
48bfb0c9b7
|
[Bug] Fix R1 Accuracy 0 Bug (#23294)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-08-21 13:11:28 -04:00 |
|
|
Yi LiuandWentao Ye
|
0278f1ac3a
|
Fix nvfp4 swizzling (#23140)
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-08-21 16:54:50 +00:00 |
|
|
Li, Jiang
|
7be5d113d8
|
[CPU] Refactor CPU W8A8 scaled_mm (#23071)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2025-08-21 09:34:24 +08:00 |
|
|
Michael Goin
|
0cdbf5e61c
|
[Kernel/Quant] Remove the original marlin format and qqq (#23204)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-20 15:13:36 -04:00 |
|
|
shixianc
|
b17109beea
|
[Kernel] CUTLASS MoE FP8: Integrate cuda moe permute/unpermute (#23045)
Signed-off-by: Shixian Cui <shixian@amazon.com>
|
2025-08-20 10:35:26 -04:00 |
|
|
amirkl94
|
a38b8af4c3
|
[NVIDIA] Add SM100 Flashinfer Cutlass MoE fp8 backend (#22357)
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
|
2025-08-19 18:01:53 -04:00 |
|
|
bnellnmandMichael Goin
|
b94faf9d50
|
[Bugfix] Fix accuracy issue when using flashinfer cutlass moe, TP=1 and modelopt. (#23125)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-08-19 14:00:51 -04:00 |
|
|
Michael Goin
|
6d25e3fd6e
|
Use Blackwell FlashInfer MXFP4 MoE by default if available (#23008)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-18 15:25:49 -07:00 |
|
|
Simon Mo
|
0fc8fa751a
|
fix: gptq marlin weight loading failure (#23066)
|
2025-08-17 15:56:07 -07:00 |
|
|
Jee Jee Li
|
4d4061b6e7
|
[Kernel] Add cuda kernel for gpt_oss activation (#22951)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-08-17 05:03:24 +00:00 |
|
|
Jinzhen Lin
|
a258ad8bcc
|
[Bugfix] fix qwen3 moe fp8 accuracy issue (#23031)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
|
2025-08-16 17:41:23 -07:00 |
|
|
Michael GoinandWentao Ye
|
4fc722eca4
|
[Kernel/Quant] Remove AQLM (#22943)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-08-16 19:38:21 +00:00 |
|
|
bnellnmandMichael Goin
|
8ad7285ea2
|
[Kernels] Clean up FusedMoeMethodBase and modular kernel setup. Remove extra arguments from modular kernel methods. (#22035)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-08-15 14:46:00 -04:00 |
|