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
1,105 Commits 25 Branches 59 Tags 2.1 GiB
7b2b657198
Commit Graph

1105 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Zhanrui Sun
7b2b657198
infra: [TRTLLM-5247][TRTLLM-5248][TRTLLM-5249] Refactor docker build image groovy and support NGC images (#4294) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-05-29 11:23:29 +08:00
QI JUN
058f83e47b
CI: move post-merge multi GPU test of PyTorch backend to H200 (#4733) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-05-29 11:15:56 +08:00
Yiqing Yan
7f29a70f53
Waive L0 test (#4748) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-05-29 11:05:27 +08:00
Yan Chunwei
ac17142495
chore: rename ExecutorBindingsWorker/Proxy (#4716) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-05-29 10:32:35 +08:00
yuanjingx87
2307e91122
[fix] add back rtx6000pro tests (#4679) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
 2025-05-29 09:22:52 +08:00
Arthur Rasmusson
812b1abf86
feature: KV Cache GPUDirect Storage (#3209) 
Signed-off-by: Arthur Rasmusson <47877520+arthurrasmusson@users.noreply.github.com.>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Co-authored-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-05-28 23:27:43 +00:00
Erin
820c39041f
chore: [nvbug_5273941] unwaive test_llm_loading_from_ckpt_for_tp2 (#4725) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-05-29 06:54:32 +08:00
Yuxian Qiu
bf691b3d28
feat: support packed weights in vanilla moe (#4719) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-29 06:24:24 +08:00
Aurelien Chartier
6cf1e4d0a9
chore: add -f to pkill calls (#4711) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-05-29 02:54:31 +08:00
Robin Kobus
12763779c4
chore: Clean up cpp runtime (#4449) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-28 16:32:59 +02:00
Ivy Zhang
ed3c67e34a
tests: [https://nvbugspro.nvidia.com/bug/5289908] run maverick bf16 on blackwell (#4722) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
 2025-05-28 22:05:51 +08:00
xinhe-nv
93283484c2
test: [CI] Add failed cases into waives.txt (#4688) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-05-28 22:04:35 +08:00
Aurelien Chartier
6b96f09ff2
chore: remove extra paths to find binaries (#4706) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-05-28 06:51:42 -07:00
Yan Chunwei
5506f60037
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-05-28 18:43:04 +08:00
ixlmar
fbe4db207d
feat: forward exceptions to Python and catch OOMs (#4497) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-05-28 11:58:10 +02:00
Yiqing Yan
66828015a0
Fix rerun step (#4715) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-05-28 17:01:05 +08:00
Iman Tabrizian
c875184f78
Add missing serialization classes (#4642) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-05-28 16:40:23 +08:00
amirkl94
fbec0c3552
Release 0.20 to main (#4577) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Venky <23023424+venkywonka@users.noreply.github.com>
Signed-off-by: Ruodi <200874449+ruodil@users.noreply.github.com>
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Signed-off-by: Simeng Liu <simengl@nvidia.com>
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
Signed-off-by: moraxu <mguzek@nvidia.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Co-authored-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
Co-authored-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
Co-authored-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Co-authored-by: Venky <23023424+venkywonka@users.noreply.github.com>
Co-authored-by: ruodil <200874449+ruodil@users.noreply.github.com>
Co-authored-by: stnie <82932102+stnie@users.noreply.github.com>
Co-authored-by: Simeng Liu <109828133+SimengLiu-nv@users.noreply.github.com>
Co-authored-by: Faraz <58580514+farazkh80@users.noreply.github.com>
Co-authored-by: Michal Guzek <moraxu@users.noreply.github.com>
Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-05-28 16:25:33 +08:00
Kaiyu Xie
b800adc65c
Fix: hang on disagg when MNNVL two-shot AllReduce is enabled (#4678) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-05-28 13:03:53 +08:00
Martin Marciniszyn Mehringer
f3fba4cc63
doc: Document the docker release image on NGC (#4705) 
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
 2025-05-28 12:00:53 +08:00
Pengyun Lin
971d16a2ee
[TRTLLM-1658][feat] Enable multiple response in trtllm-serve for TRT backend (#4623) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-05-28 11:36:44 +08:00
Bo Li
9c4b8f66b4
feat: Integration of Fused QKNorm+RoPE. (#4611) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-05-28 11:20:45 +08:00
Shunkangz
6493401986
Fix handle cancel request for attentionDP (#4648) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-05-28 11:04:02 +08:00
Yuxian Qiu
5700a4ffcd
feat: Add vanilla MOE. (#4682) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-28 10:44:14 +08:00
Martin Marciniszyn Mehringer
06eba1e061
Update the description for NGC docker images (#4671) (#4702) 
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
 2025-05-28 00:44:34 +08:00
yunruis
29ac4c20e0
fix: fix dsr1 min lat cga ar rate drop(0.2) (#4561) 
Signed-off-by: yunruis <yunruis@nvidia.com>
 2025-05-27 21:59:57 +08:00
Yuxian Qiu
e538b0d95e
refactor: extract and reuse filter_weights. (#4681) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-27 19:48:01 +08:00
xinhe-nv
bb3d998eb1
test: [CI] remove closed bugs (#4638) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-05-27 18:07:59 +08:00
Perkz Zheng
40a7161f4f
fix: fmha_v2 compilation (#4659) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-05-27 17:39:39 +08:00
Lucas Liebenwein
5cdd6bb10f
[AutoDeploy] Increased Model Coverage Mass Migration Week 1 (#4468) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: Suguna Velury <178320438+sugunav14@users.noreply.github.com>
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
Co-authored-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
Co-authored-by: sugunav14 <178320438+sugunav14@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
Co-authored-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-05-27 16:43:15 +08:00
Yiqing Yan
f6c50293d2
[Infra][TRTLLM-3929] Rerun failure tests (#3264) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-05-27 16:13:23 +08:00
Yuan Tong
5cb4f9be33
feat: improve build_wheel.py venv handling (#4525) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-05-27 15:17:14 +08:00
Yiqing Yan
92a7984945
Waive L0 tests (#4686) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-05-27 15:07:02 +08:00
QI JUN
1582361400
Chore: only pad one dummy request for attention dp scenario (#4664) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-05-27 14:56:22 +08:00
Yanchao Lu
d6e1b71388
[Test] - Correct waive the Slurm test stage (#4677) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-05-27 12:35:43 +08:00
Tracin
268171bc66
[NVBUG 5301980] Fix fp4 gemm padding. (#4662) 
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
 2025-05-27 11:30:53 +08:00
xinhe-nv
59f7622281
test: rcca https://nvbugs/5223130 (#4510) 
* add rcca tests

Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>

* skip tests on blackwell

Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>

---------

Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-05-27 09:59:47 +08:00
qsang-nv
157fe62965
fix fmha v2 tests (#4661) 
Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
 2025-05-27 09:47:01 +08:00
Yanchao Lu
258d782b0a
[Test] - Waive RTX Pro 6000 Slurm testing (#4672) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-05-27 01:17:22 +08:00
Chuang Zhu
4318037ca3
fix disagg config params (#4646) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-05-26 23:28:52 +08:00
yuanjingx87
732d92ff62
[Infra] - Multi-GPU testing support with Slurm (#4454) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-05-26 19:44:19 +08:00
Yiqing Yan
4fb8df2701
[Infra] - Add files into the scan ignore list (#4663) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-05-26 19:43:05 +08:00
Enwei Zhu
88190faa34
feat: large-scale EP(part 4: Static EP load balancer integration) (#4615) 
* MoeLoadBalancerConfig

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* MoeLoadBalancer integration

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* config file

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* test

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* test

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-05-26 18:25:11 +08:00
QI JUN
44eb053b95
introduce RequestQueueItem class instead of using tuple (#4649) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-05-26 17:34:53 +08:00
Robin Kobus
93a54457ac
[nvbugs/5274894] fix: Sort requests for functional correctness and performance (adapted from #4608) (#4621) 
- Moved sorting related logic to a dedicated function for better clarity and maintainability.
- Enhanced sorting logic to separate finished context requests from ongoing ones before sorting by Lora task ID.
- Updated function documentation to reflect the sorting behavior and its purpose.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-26 17:10:55 +08:00
Shunkangz
fd27f89df6
fix: Remove duplicate tokenization in generation server (#4492) 
* Add nvtx

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>

* Add draft change

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>

* Refactor and add support of chat

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>

---------

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-05-26 16:43:07 +08:00
Yiqing Yan
11fb00783a
[TRTLLM-5327] - Fix guardwords scan step (#4654) 
* fix scan step

Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>

* Apply suggestions from code review

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>

---------

Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-05-26 15:42:50 +08:00
Robin Kobus
502758aaa9
fix: Handle additional model outputs based on pipeline parallel rank (#4498) 
- Only allocate additional outputs on last pipeline parallel rank in trtGptModelInflightBatching and executorImpl.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-26 09:04:40 +02:00
Emma Qiao
6f626af386
[TRTLLM-4535][infra]: Add marker TIMEOUT for test level (#3905) 
* Add marker for TIMEOUT

Signed-off-by: qqiao <qqiao@nvidia.com>

* Remove workspace after tests

Signed-off-by: qqiao <qqiao@nvidia.com>

* Add missed property

Signed-off-by: qqiao <qqiao@nvidia.com>

* Add some debug info

Signed-off-by: qqiao <qqiao@nvidia.com>

* Fix errors

Signed-off-by: qqiao <qqiao@nvidia.com>

* Testing

Signed-off-by: qqiao <qqiao@nvidia.com>

* Special process for unittests

Signed-off-by: qqiao <qqiao@nvidia.com>

* Move special proecessing unittests to test generating stage

Signed-off-by: qqiao <qqiao@nvidia.com>

* Process for the whole test list

Signed-off-by: qqiao <qqiao@nvidia.com>

* Test more

Signed-off-by: qqiao <qqiao@nvidia.com>

* Add another test case

Signed-off-by: qqiao <qqiao@nvidia.com>

* Change back the setting for testing

Signed-off-by: qqiao <qqiao@nvidia.com>

* Revert another config file

Signed-off-by: qqiao <qqiao@nvidia.com>

* Add descriptionf or timeout in test readme

Signed-off-by: qqiao <qqiao@nvidia.com>

---------

Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-05-25 23:30:40 -07:00
Zheng Duan
ce7f5fae5a
sort llm request state (#4607) 
Signed-off-by: Zheng Duan <200704041+zhengd-nv@users.noreply.github.com>
 2025-05-26 13:47:01 +08:00