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
232 Commits 25 Branches 59 Tags 2.1 GiB
992d513bc6
Commit Graph

232 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jinyang Yuan
992d513bc6
feat: Optionally split MoE inputs into chunks to reduce GPU memory usage (#3104) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
Co-authored-by: raccoonliukai <raccoonliu@tencent.com>
 2025-04-01 16:07:02 +08:00
brb-nv
727d78e785
Support prequantized fp8 ckpt for nemotron-mini-4b-instruct (#3046) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-04-01 14:52:09 +08:00
Yan Chunwei
7575dd00e7
add slurm script examples for llm-api (#3135) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-04-01 14:31:57 +08:00
Yuan Tong
2994527110
chore: cutlass cleanup (#3165) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-04-01 13:57:38 +08:00
dongjiyingdjy
22ff81b047
fix：fix illeagel memory access when mtp >= 2 (#3006) 
* fix - fix illeagel memory access when mtp > 2

---------

Signed-off-by: Jiying Dong <87510204+dongjiyingdjy@users.noreply.github.com>
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-04-01 13:36:45 +08:00
QI JUN
75495730bc
Revert "refactor: Replace DecoderFinishedEvent with CudaEvent in decoder clas…" (#3183) 
This reverts commit 3ee4332fb1.

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-04-01 12:49:27 +08:00
Shunkangz
dda7354d1a
Refactor return of first gen token in PD (#2986) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-04-01 12:28:27 +08:00
brb-nv
1901bfcf76
test: Add Eagle tests with untrained heads (#2991) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-04-01 11:41:59 +08:00
jiahanc
c4ee14e43a
fix: Reverse cuda graph size order (#3116) 
Signed-off-by: jiahanc <jiahanc@nvidia.com>
 2025-04-01 11:28:36 +08:00
Erin
68bcd0ac07
doc: update README (#3162) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-04-01 10:37:06 +08:00
Aurelien Chartier
14e194433c
chore: cleanup py_executor code (#3132) 
* chore: cleanup py_executor code

* Add common loop cleanup function
* Remove checks for attention DP if nothing to queue
* Remove extra return statements
* Remove extra variables
* Remove commented debug print

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>

* rename cleanup function

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>

---------

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
 2025-04-01 09:27:04 +08:00
Anurag Mukkara
435cd2983d
perf: Optimisations for PP + attention DP (#3134) 
* Minor tp_rank fix

Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>

* Delete unused function

Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>

* PP broadcast for ADP new requests

Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>

* Sync request finish point for intermediate and last pp ranks

Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>

* Use local PP layers only for KV cache estimation

Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>

---------

Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
 2025-04-01 08:59:16 +08:00
Frank
8bb3eea285
perf: Readd iteration logging for trtllm-bench. (#3039) 
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
 2025-04-01 08:13:09 +08:00
Iman Tabrizian
e8731ba3b7
fix: disable cuda graph and MTP for overlap tests (#3155) 
Signed-off-by: Iman Tabrizian <itabrizian@nvidia.com>
 2025-03-31 11:35:35 -07:00
WeiHaocheng
f665f83256
feat: improve scaffolding shutdown process (#3084) 2025-03-31 20:39:20 +08:00
Zhanrui Sun
36ac5e78ed
chore: bump version to 0.19.0.dev2025040100 (#3152) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-03-31 16:36:06 +08:00
Quanfeng Li
839aad4d6e
fix: Add missing parameter for WeightOnlyQuantRowLinear module (#2768) 
Signed-off-by: Quanfeng Li <liquanfeng7@foxmail.com>
 2025-03-31 16:20:30 +08:00
QI JUN
9560fcd5ec
Chore: waive tests and fix multi-GPU tests (#3157) 
* waive tests

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* update

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* clean up

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

---------

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-03-31 16:05:45 +08:00
bhsueh_NV
322ac565fc
chore: clean some ci of qa test (#3083) 
* move some models to examples/models/contrib

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* update the document

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* remove arctic, blip2, cogvlm, dbrx from qa test list

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* remove tests of dit, mmdit and stdit from qa test

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* remove grok, jais, sdxl, skywork, smaug from qa test list

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* re-organize the glm examples

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* fix issues after running pre-commit

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* fix some typo in glm_4_9b readme

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* fix bug

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

---------

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-03-31 14:30:41 +08:00
Zhanrui Sun
1e1116ccfc
infra: Switch to urm.nvidia.com as a WAR for urm-rn.nvidia.com connection issue 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-03-31 13:05:29 +08:00
xinhe-nv
86f3b59f81
update waive list (#3094) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Co-authored-by: larryx <larryx@nvidia.com>
 2025-03-31 11:42:45 +08:00
liji-nv
e0d0dde058
None - Add one-shot version for UB AR NORM FP16/BF16 (#2995) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-03-31 11:16:03 +08:00
Yan Chunwei
794f61c997
fix: fix single-node cannot quit issue on slurm (#3140) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-03-31 10:15:27 +08:00
musvaage
88e1c90fd0
doc: use alert formatting (#3153) 
Signed-off-by: musvaage <musvaage@users.noreply.github.com>
Co-authored-by: musvaage <musvaage@users.noreply.github.com>
 2025-03-31 07:30:52 +08:00
Yiteng Niu
3aae124a00
infra: update concurrency control (#3120) 
* update concurrency control

Signed-off-by: Yiteng Niu <6831097+niukuo@users.noreply.github.com>

* Update .github/workflows/blossom-ci.yml

Co-authored-by: tburt-nv <195370667+tburt-nv@users.noreply.github.com>
Signed-off-by: Yiteng Niu <6831097+niukuo@users.noreply.github.com>

---------

Signed-off-by: Yiteng Niu <6831097+niukuo@users.noreply.github.com>
Co-authored-by: tburt-nv <195370667+tburt-nv@users.noreply.github.com>
 2025-03-30 23:28:50 +08:00
Mike Iovine
5416966ddb
Add initial EAGLE-3 implementation (#3035) 
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-03-29 22:31:24 +08:00
William Tambellini
9c484b24e6
fix #3109: early exit cmake if find_library() does not find any lib (#3113) 
Early exit if find_library() does not find any lib.
As today, the find_library_create_target() cmake macro
blindly continues even if the lib is not found,
adding LIB_PATH-NOTFOUND to the target and making the build
failing anyway later with non obvious reasons.
This change just early exits if the lib is simply not found with a
proper error message.
Fix github issue #3109

Signed-off-by: William Tambellini <wtambellini@sdl.com>
 2025-03-29 19:59:03 +08:00
Erin
c75d7cd684
move BuildConfig functional args to llmargs (#3036) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-03-29 02:20:18 +08:00
Robin Kobus
3ee4332fb1
refactor: Replace DecoderFinishedEvent with CudaEvent in decoder classes (#3078) 
- Updated the `forwardAsync` method in `GptDecoderBatched` and `iGptDecoderBatched` to return `CudaEvent` instead of `DecoderFinishedEventPtr`, simplifying event handling.
- Removed the `DecoderFinishedEvent` class and its associated usage across various files, streamlining the codebase.
- Adjusted related methods and Python bindings to accommodate the new event structure, ensuring compatibility and maintaining functionality.

These changes enhance the clarity and efficiency of the decoding process in the batch manager.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-03-28 14:50:52 +08:00
Robin Kobus
45134d7095
refactor: Improve decoder finalize function (#3077) 
* refactor: Update gatherTree function to accept CUDA stream parameter

This commit modifies the gatherTree function signature to include a runtime::CudaStream parameter, enhancing flexibility in stream management. Additionally, it removes unnecessary buffer manager parameters and stream handling from the function, streamlining the code. The finalize method in GptDecoderBatched is also updated to reflect these changes, improving clarity and maintainability in the decoding process.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Update GptDecoderBatched finalize

This commit refactors the GptDecoderBatched class to improve method signatures and reduce code complexity:

- Modified finalize method to accept DecoderState as a parameter
- Updated method signatures to work with the new DecoderState approach
- Improved code organization and readability

The changes continue the ongoing refactoring to centralize decoder state management and simplify the decoder implementation.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-03-28 14:33:59 +08:00
BatshevaBlack
3e37531c6a
feat: Add BW measurement (#3070) 2025-03-28 10:53:00 +08:00
Aurelien Chartier
3de82c41cd
Pytorch PP + attention DP support (#3044) 
Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
 2025-03-28 00:11:19 +08:00
Fanrong Li
ec03159e60
fix: Waive twoshot to fix acc issue (#3066) 
* waive twoshot to fix acc issue

Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>

---------

Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-03-27 21:38:52 +08:00
Fanrong Li
644a01cbbe
test: Add gpqa tests for DeepSeek models (#3063) 
* Add gpqa accuracy test script
* Add gpqa accuracy tests
* Update DeepSeek-v3 doc
* Update qa test list

---------

Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-03-27 19:47:06 +08:00
Yan Chunwei
87ab794aa2
fix: fix hang in mgmn with trtllm-llmapi-launch command (#3119) 
* init

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

* restore

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

---------

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-03-27 18:45:43 +08:00
Fanrong Li
0976360204
add support for MTP+cuda_graph_padding. (#3096) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-03-27 16:06:14 +08:00
xiweny
6979afa6f2
test: reorganize tests folder hierarchy (#2996) 
1. move TRT path tests to 'trt' folder
2. optimize some import usage
 2025-03-27 12:07:53 +08:00
Yan Chunwei
82edd90350
fix gpus_per_node in trtllm-bench when world_size < device_count (#3007) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-03-27 09:31:40 +08:00
Dom Brown
60d4dacc47
Port multi GPU changes to GitHub (#3027) 
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-03-27 05:55:03 +08:00
Suyog Gupta
047f2b234d
perf: [AutoDeploy] Enable AutoDeploy as a backend in trtllm-bench (#3041) 
* Enable AutoDeploy as a backend in trtllm-bench

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* update how caches are resized

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* fix: files permission from 100755 to 100644

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* some comments

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* lint

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* lint

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* lint

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* lint

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* Fix function name

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* refactor

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* Remove spurious change

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* Add cursor generated doc strings

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* re-enable ad test

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* some perf cleanup

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* debug ci

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* ensure that overlap scheduler is enabled

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

* Reorder the tests

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>

---------

Signed-off-by: Suyog Gupta <suyogg@nvidia.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-03-26 14:33:14 -07:00
wili
3e035f2219
v1.2 (#3082) 
Signed-off-by: wili <wili@nvidia.com>
 2025-03-26 23:31:29 +08:00
Robin Kobus
d9522c5906
feat: Update cutlass (#2981) 
* chore: update cutlass to v3.8.0

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: update include directives for consistency and organization in weightOnlyBatchedGemv headers

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* Fix fpA_intB_gemm compilation

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-03-26 22:36:27 +08:00
Jinyang Yuan
6b583f6f83
perf: Enable CUDA graphs when attention DP is used and active requests on different GPUs are uneven (#3010) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
Co-authored-by: raccoonliukai <raccoonliu@tencent.com>
 2025-03-26 21:09:25 +08:00
Robin Kobus
3c3629c52a
refactor: simplify forward methods in GptDecoderBatched (#3076) 
* refactor: Remove ForwardType enum from GptDecoderBatched

 - Remove ForwardType enum from GptDecoderBatched
 - Simplify forwardDispatch and forwardDecoder methods

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Remove forwardDecoder method from GptDecoderBatched

- Eliminate the forwardDecoder method to streamline the decoding process.
- Update forwardDispatch to directly call forwardAsync when input batch size is greater than zero.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Move event handling from forwardDispatch to forwardAsync

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-03-26 20:45:04 +08:00
Robin Kobus
94dd456bd0
refactor: Remove speculative decoding parameters from stateful decoders (#3024) 
Simplify StatefulGptDecoderBatched constructor:
  - Remove speculative decoding mode parameter
  - Initialize with default mode=None
  - Update GptSession class accordingly

Simplify setup method signatures in StatefulGptDecoder and StatefulGptDecoderBatched:
  - Remove maxTokensPerStep parameter
  - Initialize decoders with default maxTokensPerStep=1
  - Update GptSession class accordingly

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-03-26 20:16:26 +08:00
Dom Brown
f995a92a31
CI: Waive for https://nvbugspro.nvidia.com/bug/5189673 (#3100) 
* Waive for https://nvbugspro.nvidia.com/bug/5189673

Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>

* Update waive

Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>

---------

Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-03-26 19:13:43 +08:00
Enwei Zhu
224469b096
test: [TRTLLM-4334] Create 1.0 criteria scope from API stability references (#3069) 
* committed APIs validation

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

* fix

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

* clean name

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

* separate

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

* add TODOs

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

* fix naming

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>
 2025-03-26 18:14:35 +08:00
Kaiyu Xie
ea3739ee62
Fix: fuse message not aligned on different processes (#3067) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-03-26 17:15:27 +08:00
Zheng Duan
d70ff79d1d
conditional disagg test (#3012) 
Signed-off-by: Zheng Duan <200704041+zhengd-nv@users.noreply.github.com>
 2025-03-26 15:55:33 +08:00
Ivy Zhang
3e116c9687
test: add random image test for llama-3.2-11b-vision (#3055) 
* add random image test for llama-3.2-11b-vision

Signed-off-by: Ivy Zhang <yanzh@nvidia.com>

* rename case

Signed-off-by: Ivy Zhang <yanzh@nvidia.com>

---------

Signed-off-by: Ivy Zhang <yanzh@nvidia.com>
Co-authored-by: Larry <larryx@nvidia.com>

CI got Passed: https://nv/trt-llm-cicd/job/helpers/job/PR_Github/522/
 2025-03-26 15:38:16 +08:00