Commit Graph

31 Commits

Author SHA1 Message Date
Xiwen Yu
52ad4436bc disable 3xfp4
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
2025-08-06 14:25:05 +08:00
Daniel Stokes
469a38d0d8 feat: Add support for SM103 3xFP4 tile shapes
Signed-off-by: Daniel Stokes <dastokes@nvidia.com>
2025-08-06 14:25:02 +08:00
Xiwen Yu
303604f82d upgrade to base image and new TRT, fix many dependency issues
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
2025-08-06 14:24:37 +08:00
Yiqing Yan
3f7abf87bc
[TRTLLM-6224][infra] Upgrade dependencies to DLFW 25.06 and CUDA 12.9.1 (#5678)
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
2025-08-03 11:18:59 +08:00
nv-guomingz
49044733e1
chore: delete useless gitkeep files. (#6400)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-07-28 11:38:30 -04:00
Iman Tabrizian
bc2fb29c5e
[nvbugs/5401261][fix] Fix Triton backend disaggregated serving support (#6224)
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
2025-07-23 05:27:16 +08:00
pcastonguay
310bdd9830 fix: Fix triton backend build [nvbug 5396469] (#6098)
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
2025-07-22 12:48:00 +08:00
amirkl94
f4f2176cd5 chore: Port leftover 0.20 (#5907)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Yingge He <yinggeh@nvidia.com>
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Co-authored-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: Yingge He <157551214+yinggeh@users.noreply.github.com>
Co-authored-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Co-authored-by: zpatel <22306219+zbpatel@users.noreply.github.com>
2025-07-22 12:48:00 +08:00
Simeng Liu
4a0951f85c
[Chore] Replace MODEL_CACHE_DIR with LLM_MODELS_ROOT and unwaive triton_server/test_triton.py::test_gpt_ib[gpt-ib] (#5859)
Signed-off-by: Simeng Liu <simengl@nvidia.com>
2025-07-21 15:46:37 -07:00
Aurelien Chartier
6a47cac981
feat: Add support for Triton request cancellation (#5898)
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
2025-07-15 20:52:43 -04:00
Chang Liu
308776442a
[nvbug/5308432] fix: extend triton exit time for test_llava (#5971)
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-07-12 12:56:37 +09:00
Aurelien Chartier
3ec3ff1d82
chore: remove support for llmapi + TRT backend in Triton (#5856)
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
2025-07-09 21:30:34 -07:00
Vivian Chen
34212e2e36
[TRTLLM-6104] feat: add request_perf_metrics to triton LLMAPI backend (#5554)
Signed-off-by: Vivian Chen <140748220+xuanzic@users.noreply.github.com>
2025-06-30 21:34:42 -07:00
nv-guomingz
578430e64c
[TRTLLM-5530][BREAKING CHANGE]: enhance the llm args pytorch config part 1(cuda_graph_config) (#5014)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-06-30 11:05:40 +08:00
Iman Tabrizian
26b953e29a
[nvbugs/5309940] Add support for input output token counts (#5445)
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
2025-06-28 04:39:39 +08:00
wili
56cdfe5c6c
[TRTLLM-5000][feat] NGrams V2 (#4569)
Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>
Co-authored-by: wili-65535 <wili-65535@users.noreply.github.com>
2025-06-27 23:00:17 +08:00
Iman Tabrizian
49af791f66
Add testing for trtllm-llmapi-launch with tritonserver (#5528)
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
2025-06-27 11:19:52 +08:00
Robin Kobus
8dfa31c71d
refactor: remove batch_manager::KvCacheConfig and use executor::KvCacheConfig instead (#5384)
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
2025-06-26 19:45:52 +08:00
Yan Chunwei
9bd42ecf9b
[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default (#5312)
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
2025-06-20 03:01:10 +08:00
Aurelien Chartier
e1e5f725fc
fix: only set _mpi_session if world_size is > 1 (#5253)
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
2025-06-17 19:21:41 -07:00
Emma Qiao
ff32caf4d7
[Infra] - Update dependencies with NGC PyTorch 25.05 and TRT 10.11 (#4885)
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Signed-off-by: Emma Qiao <qqiao@nvidia.com>
Co-authored-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Co-authored-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
2025-06-17 23:48:34 +08:00
Aurelien Chartier
82e280f6f3
feat: add multi-node support for Triton with pytorch backend (#5172)
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
2025-06-13 13:27:58 -07:00
Chang Liu
f70815c945
[TRTLLM-5007][feat] Add multimodal hashing support (image hashing) (#4145)
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Co-authored-by: hlu1 <14827759+hlu1@users.noreply.github.com>
2025-06-10 01:59:56 +08:00
pcastonguay
5b84fd9201
[nvbug 5283506] fix: Fix spec decode triton test (#4845)
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
2025-06-09 08:40:17 -04:00
Bo Li
f414a079ad
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2025-06-07 16:10:47 +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
Iman Tabrizian
e741d2b8d0
Add tritonrelease container (#4455)
* Add tritonrelease container

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* Review comments

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* Update docker/Makefile

Co-authored-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>

---------

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
2025-05-21 23:47:50 -04:00
Aurelien Chartier
f491244c84
feat: add dataset support for benchmark_core_model with LLMAPI (#4457)
* feat: add dataset support for benchmark_core_model with LLMAPI

Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
2025-05-21 19:18:43 -07:00
Aurelien Chartier
1681e9fd1e
chore: remove extra PYTHONPATH (#4453)
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
2025-05-21 17:38:01 -07:00
Iman Tabrizian
4c7191af67
Move Triton backend to TRT-LLM main (#3549)
* Move TRT-LLM backend repo to TRT-LLM repo

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* Address review comments

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* debug ci

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* Update triton backend

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* Fixes after update

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

---------

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
2025-05-16 07:15:23 +08:00