kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
1,510 Commits 25 Branches 59 Tags 2.1 GiB
490d2e5819
Commit Graph

1510 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
dongxuy04
490d2e5819
feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) (#5226) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-06-25 22:25:13 -07:00
amitz-nv
e0bb123ae7
[TRTLLM-5921][feat] Prevent serialization of entire LoRA adapters in each request (#5080) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-06-26 08:15:06 +03:00
Yukun He
9ee33605bb
[TRTLLM-6019] feat: Remove cutlass min latency code from AutoTuner. (#5394) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-06-26 13:12:03 +08:00
Daniel Stokes
942841417e
opensource: Opensource MOE MXFP8-MXFP4 implementation (#5222) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-06-26 12:18:19 +08:00
qsang-nv
e9cd810071
keep sm90 headsize 128 cubins (#5320) 
Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
 2025-06-26 12:14:01 +08:00
Netanel Haber
6aef14943c
Revert "feature: unify new_tokens format sample state to trtllm samper new_tokens format (#4401)" (#5474) 
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2025-06-25 20:56:04 -07:00
Emma Qiao
32d1573c43
[Infra] - Add timeout setting for long tests found in post-merge (#5501) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-06-26 11:31:39 +08:00
Venky
d9b75f83fd
[CI] Waive test_fp8_block_scales_4gpus[ep4-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] (#5494) 
Signed-off-by: Venky <23023424+venkywonka@users.noreply.github.com>
 2025-06-25 20:17:12 -07:00
ChristinaZ
d135f5993d
Add unit test for routing kernels (#5405) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-06-26 09:49:11 +08:00
jmydurant
578dbc8d9a
feat: chunked prefill for MLA (Blackwell) (#4651) 
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2025-06-26 09:01:00 +08:00
Yukun He
3fc57543e2
[5356427] fix: Remove the seq_len of 4096 from FP8 block scale MoE tuning configs. (#5485) 
The seq_len of 4096 will cause some unknown CUDA illegal memory access issue if run with some other tests consecutively.
Put a saturated upper bound for any sequence length larger than it.
 2025-06-26 08:38:35 +08:00
HuiGao-NV
74ae15a26b
CI: enable test cases on single device type (#5484) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-26 08:03:44 +08:00
Xianjie Qiao
1e4fa13d33
Add sleep function for disagg gen-only benchmarking (#5398) 
Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
 2025-06-26 07:32:16 +08:00
QI JUN
feaf789342
CI: reduce BF16 test cases in B200 (#5482) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-06-26 07:18:20 +08:00
Omer Ullman Argov
bdc8dfebc3
[fix][ci] dont build wheel for cpp tests (#5443) 
Signed-off-by: Omer Ullman Argov <118735753+omera-nv@users.noreply.github.com>
 2025-06-26 00:13:47 +03:00
Omer Ullman Argov
61bb71fd1b
[fix][test] remove test in global scope (#5470) 
Signed-off-by: Omer Ullman Argov <118735753+omera-nv@users.noreply.github.com>
 2025-06-25 23:42:26 +03:00
QI JUN
3a2c4ca77b
chore: split _build_model method for TorchLlm and TrtLlm (#5418) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-06-26 04:32:46 +08:00
Mike Iovine
5bc8c894f7
[chore] Disable block reuse when draft model speculation is being used (#5448) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-06-26 03:51:20 +08:00
Daniel Cámpora
205c97a4ae
[TRTLLM-5974][feat] Support disaggregated serving in TRTLLM Sampler (#5328) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-06-25 17:41:36 +02:00
Kaiyu Xie
c5ae3272b9
feat: Make benchmark_serving part of the library (#5428) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-06-25 23:13:56 +08:00
HuiGao-NV
314f15f0a7
Fix: fix nvbug 5356427 (#5464) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-25 22:24:26 +08:00
HuiGao-NV
cc3c2b3be2
Move 3 disaggregated cases from 4 GPUs devices to 1 GPU device (#5457) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-25 21:38:14 +08:00
Kaiyu Xie
d6ada5ffce
[nvbug/5354956] fix: unexpected keyword argument 'streaming' (#5436) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-06-25 20:37:24 +08:00
HuiGao-NV
b3a4c1f404
feat: Remove not used padding_idx in models (#5385) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-25 17:19:59 +08:00
QI JUN
2901c5a5bc
CI: waive test_ad_build_small_multi (#5471) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-06-25 16:44:42 +08:00
Perkz Zheng
1f292ff2a0
[https://jirasw.nvidia.com/browse/TRTLLM-4645] support mutliCtasKvMode for high-throughput MLA kernels (#5426) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-06-25 16:31:10 +08:00
Yiqing Yan
f3cfe86dd1
chore: bump version to 1.0.0rc1 (#5460) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-06-25 16:21:34 +08:00
Netanel Haber
3ca2f6ac51
start OAIServer with max_beam_width=1 for TorchSampler (#5427) 
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
 2025-06-25 15:52:06 +08:00
QI JUN
478f668dcc
CI: update multi gpu test triggering file list (#5466) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-06-25 15:51:02 +08:00
Enwei Zhu
fc7a81ceb0
test: Add LLGuidance test and refine guided decoding (#5348) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-06-25 14:12:56 +08:00
Enwei Zhu
76da7fed86
fix (NvBug 5354925): Fix static EPLB (#5411) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-06-25 13:14:40 +08:00
HuiGao-NV
da98e03747
tests: Set kv cache free memory fraction in test case (#5433) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-25 12:31:58 +08:00
Shunkangz
d5354897c0
feat: Dynamically remove servers in PD (#5270) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-06-25 09:50:04 +08:00
Lucas Liebenwein
5cffb7e0ec
[AutoDeploy] Merge feat/ad_2025_06_13 feature branch (#5454) 
Signed-off-by: Grzegorz Kwasniewski <213329731+greg-kwasniewski1@users.noreply.github.com>
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: Grzegorz Kwasniewski <213329731+greg-kwasniewski1@users.noreply.github.com>
Co-authored-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
Co-authored-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
 2025-06-25 09:30:13 +08:00
bhsueh_NV
73ba4fc320
fix: fix bug of qwen3 + eagle3 + finalize_moe_fusion (#5369) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-06-25 09:20:23 +08:00
QI JUN
241f921800
waive test_moe.py::test_moe_fp8[autotune] (#5455) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-06-25 09:14:44 +08:00
dongxuy04
699520082b
Add MTP support for Online EPLB (#5213) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-06-25 07:58:13 +08:00
Iman Tabrizian
846bbf1edc
Fix test Pytorch model engine (#5416) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-06-24 11:09:27 -07:00
QI JUN
d93a5e04b5
Chore: remove unused variables (#5314) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-06-24 22:27:32 +08:00
HuiGao-NV
35a92f6bab
Add debug hook to support dump tensor data and add new debug functions easily (#5182) 
Signed-off-by: Hui Gao
 2025-06-24 17:45:28 +08:00
Emma Qiao
475272046a
[Infra] - Waive failed tests in post-merge and increase some timeout setting (#5424) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-06-24 17:19:31 +08:00
Luis Vega
d26040e5d9
chore: delete mamba hybrid, since it is now called NemotronH (#5409) 
Signed-off-by: Luis Vega <vegaluisjose@users.noreply.github.com>
 2025-06-24 16:27:31 +08:00
xinhe-nv
658fb5b54e
tests: update benchmark test lists (#5365) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-06-24 15:23:38 +08:00
Robin Kobus
e2a8cbc80b
refactor: manage cache indirection in decoder state (#5315) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-24 09:15:59 +02:00
xinhe-nv
4b32a3f1a7
test: [CI] remove closed bugs (#5400) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-06-24 13:39:57 +08:00
HuiGao-NV
e16c1bef6e
[fix] Add 1 and draft_token_num to seq_len when overlap scheduling is enabled during memory estimation (#5343) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-24 11:43:43 +08:00
Netanel Haber
58a8a8fd37
feature: unify new_tokens format sample state to trtllm sampler new_tokens format (#4401) 
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2025-06-23 10:38:37 -07:00
Fanrong Li
ebadc13086
[doc] update mtp documents (#5387) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-06-21 16:05:52 +08:00
Robin Kobus
b3045c44b9
refactor: remove TrtGptModelOptionalParams (#5165) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-20 10:31:40 +02:00
dongxuy04
4f0f17ac8a
feat: Misc Opt for large scale EP (#5374) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-06-20 13:11:31 +08:00