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
3,373 Commits 25 Branches 59 Tags 2.1 GiB
24167d00eb
Commit Graph

474 Commits

Author SHA1 Message Date
Lizhi Zhou
24167d00eb
[TRTLLM-8431][doc] update public doc and example, add etcd auto-scaling tests (#8602) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-10-28 17:04:53 -07:00
Anish Shanbhag
a09b38a862
[TRTLLM-8684][chore] Migrate BuildConfig to Pydantic, add a Python wrapper for KVCacheType enum (#8330) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2025-10-28 09:17:26 -07:00
Aurelien Chartier
0a02f5f25d
[None][chore] Use a cached model path for Ray integration test (#8660) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-10-27 19:16:06 -07:00
gramnarayan
88b0fbc8ff
[#8245][feat] Autodeploy: Guided Decoding Support (#8551) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Co-authored-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-28 09:29:57 +08:00
nvxuanyuc
d1398c05e6
[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127) 
Signed-off-by: Xuanyu Chen <xuanyuc@nvidia.com>
 2025-10-27 13:12:31 -04:00
zhanghaotong
1026069a2b
[None][feat] Add opentelemetry tracing (#5897) 
Signed-off-by: Zhang Haotong <zhanghaotong.zht@antgroup.com>
Signed-off-by: zhanghaotong <zhanghaotong.zht@antgroup.com>
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Zhang Haotong <zhanghaotong.zht@alibaba-inc.com>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-10-27 18:51:07 +08:00
Robin Kobus
990b0c0c47
[TRTLLM-7159][docs] Add documentation for additional outputs (#8325) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-10-27 09:52:04 +01:00
Chang Liu
e47c787dd7
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
 2025-10-24 13:40:41 -04:00
Yechan Kim
2d86d6be40
[TRTLLM-8737][feat] Support media_io_kwargs on trtllm-serve (#8528) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-10-24 12:53:40 -04:00
QI JUN
6ee1c87595
[TRTLLM-8817][chore] Set default value of KvCacheConfig.free_gpu_memory_fraction explicitly (#8561) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-24 08:55:49 +08:00
Anish Shanbhag
15de45d782
[TRTLLM-8682][chore] Remove auto_parallel module (#8329) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2025-10-22 20:53:08 -04:00
Patrice Castonguay
879039f6d5
[https://nvbugs/5429636][feat] Kv transfer timeout (#8459) 
Signed-off-by: raayandhar <raayan.dhar@gmail.com>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: raayandhar <raayan.dhar@gmail.com>
 2025-10-22 09:29:02 -04:00
Yiqing Yan
b04e51291a
[None][chore] Bump version to 1.2.0rc2 (#8562) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-10-22 14:35:05 +08:00
Shi Xiaowei
50149ac2bd
[None][doc] Fix the incorrect doc figure (#8536) 
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-10-22 10:08:55 +08:00
Zero Zeng
4545700fcf
[None][chore] Move submit.sh to python and use yaml configuration (#8003) 
Signed-off-by: Zero Zeng <38289304+zerollzeng@users.noreply.github.com>
 2025-10-20 22:36:50 -04:00
Bo Deng
dd25595ae8
[TRTLLM-7964][infra] Set nixl to default cache transceiver backend (#7926) 
Signed-off-by: Bo Deng <deemod@nvidia.com>
 2025-10-19 19:24:43 +08:00
h-guo18
55fed1873c
[None][chore] AutoDeploy: cleanup old inference optimizer configs (#8039) 
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-17 15:55:57 -04:00
Cao Dong
e75b4f9f65
[None][feat] Dev DeepConf (#8362) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-10-16 11:01:31 +08:00
mpikulski
93a4b7f1b6
[None][chore] update torch_dtype -> dtype in 'transformers' (#8263) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-15 17:09:30 +09:00
Erin
f4e7738f65
[None][doc] Ray orchestrator initial doc (#8373) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-10-14 21:17:57 -07:00
Lucas Liebenwein
43c46a09db
[None][chore] AutoDeplopy: Update expert section on yaml configuration in README (#8370) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-14 12:39:28 -04:00
Fanrong Li
0d20a8fd61
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
Co-authored-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
 2025-10-14 08:23:16 -07:00
Cao Dong
62cea877b1
[None][feat] Move StreamGeneration to scaffolding main directory (#8347) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-10-14 17:16:04 +08:00
Robin Kobus
db8c63b9b1
[TRTLLM-4517] [feat] Additional model outputs (#7206) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-10-13 15:33:18 +02:00
Xianjie Qiao
d145e87f6f
[None][chore] Update disagg benchmark configs (#8289) 
Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
Signed-off-by: Xianjie Qiao <5410381+qiaoxj07@users.noreply.github.com>
 2025-10-13 18:15:46 +08:00
Jonas Yang CN
88ea2c4ee9
[TRTLLM-7349][feat] Adding new orchestrator type -- ray (#7520) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Co-authored-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
Co-authored-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-10-04 08:12:24 +08:00
Lucas Liebenwein
aaf2c3c2e5
[None][feat] AutoDeploy: compiler backends based on nn.Module (#8126) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-03 12:14:21 -04:00
Lucas Liebenwein
5faa5e9dd8
[None][feat] AutoDeploy: dive deeper into token generation bugs + enable_block_reuse (#8108) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-03 04:57:26 -07:00
Yechan Kim
e9e4632e44
[None][doc] Add more description on EXAONE usage (#8089) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-09-30 21:32:43 -04:00
Yiqing Yan
1560cca227
[None][chore] Bump version to 1.2.0rc1 (#8097) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-09-30 06:00:25 -04:00
bhsueh_NV
38d6e4e60b
[None][feat] Support Qwen3 next (#7892) 
Signed-off-by: mengw <12670782+wm2012011492@users.noreply.github.com>
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-09-29 21:16:07 +08:00
Yiqing Yan
560ded5450
[None][chore] Bump version to 1.2.0rc0 (#7941) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-09-29 17:39:07 +08:00
Kaiyu Xie
030254f88a
[None] [doc] Document hang issue caused by UnpicklingError (#8049) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-09-28 23:40:35 -04:00
Zongfei Jing
e9f26feeb6
[None][chore] Cherry-pick from (#7598) Make low_precision_combine as a llm arg (#7898) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-09-28 22:32:33 -04:00
YueWeng
a4243f0da5
[TRTLLM-6393][feat] add static tree sampling and verification (#7161) 
Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
 2025-09-26 13:16:16 -04:00
Guoming Zhang
202bed4574 [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-25 21:02:35 +08:00
Guoming Zhang
9f0f52249e [None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-25 21:02:35 +08:00
Yueh-Ting (eop) Chen
cf100933cc
[TRTLLM-6341][feature] Support SWA KV cache reuse (#6768) 
This merge request attempts to support more SWA KV cache functionality
inside the KV cache manager. Before this merge request, the KV cache for
sliding window attention (SWA) only holds "window size" number of blocks
and reuse them in a cyclic manner. We will not be able to utilize more
GPU memory with this design, leading to a limited max batch size
throughput. Additionally, we will not be able to support KV cache reuse
with this design.

In this MR, we change such behavior to let the manager write blocks in
a linear manner. With a linear block writing behavior, as the attention
window moves on, the out-of-window (OOW) blocks will be detached. Right
now for the sake of a correct feature first, we directly offload the
OOW block from the primary block pool (GPU memory) to the secondary
block pool (host memory). We will improve this in the future by
delegating the block movement to the eviction policy.

KV cache reuse for SWA is not developed in this merge request and will
be amended in a follow-up merge request.

Writing the blocks linearly, the maximum number of blocks allocated for
a sequence(`GenerationRequest`) is the "max sequence length" specified.
The `GenerationRequest` that stores the cache block bookkeeping
structure will now keep "max sequence length" tokens of blocks.

Given the above, main changes are (more context in the MR):
- Remove "cyclic" concept under the kv cache manager, such concept
  originally guards the block reuse under kv cache manager.
- Add detach mechanism and have it under `KVCacheManager::addToken`.
  Please note that detach is still guarded off for SWA when reuse
  is enabled. A follow-up merge request will proceed to improve this.
- Enforce "max sequence length" to be a non-optional parameter to
  the `KVCacheManager`/`BlockManager`
- Let all window size resource pool get identical proportion of memory
- Fix free memory calculation under `resource_manager.py`

Signed-off-by: eopXD <yuehtingc@nvidia.com>
Co-authored-by: Tomer Asida <tasida@nvidia.com>
 2025-09-24 14:28:24 +08:00
Zero Zeng
16bb76c31d
[None][chore] Update benchmark script (#7860) 
Signed-off-by: Zero Zeng <38289304+zerollzeng@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-09-23 03:15:42 -07:00
Yechan Kim
f77aca9f2c
[TRTLLM-7385][feat] Optimize Qwen2/2.5-VL performance (#7250) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-09-22 03:40:02 -07:00
dongxuy04
9eb8084ca9
[TRTLLM-7008][fix] cherrypick to main Add automatic shared memory delete if already exist (#7727) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-09-21 11:01:51 -07:00
Yuxian Qiu
7d28acdbf0
[https://nvbugs/5522332][fix] Pin numpy version for Gemma. (cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/7783) (#7797) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-09-19 18:50:40 +08:00
Kyungmin Lee
6fcc0540f0
[None][fix] fix load_model_on_cpu on qwen/convert_checkpoint.py (#2382) 
Signed-off-by: lkm2835 <lkm2835@gmail.com>
Co-authored-by: Kanghwan <861393+karljang@users.noreply.github.com>
 2025-09-18 21:54:26 -07:00
sunnyqgg
80dd8fe197
[TRTLLM-6746][feat] Enable two-model spec dec for MTP Eagle (#7001) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-09-18 12:05:36 -04:00
Yanchao Lu
f8e811d134
[None][chore] Version bump for 1.1.0rc6 (#7824) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-09-18 11:13:56 +08:00
Lucas Liebenwein
39eb120b96
[#7308] [feat] AutoDeploy: graph-less transformers mode for HF (#7635) 
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
 2025-09-18 10:44:24 +08:00
QI JUN
d3467f9f12
[None][doc] fix section header of llm_kv_cache_offloading example (#7795) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-09-17 17:26:11 +08:00
QI JUN
39248320d4
[None][feat] add an example of KV cache host offloading (#7767) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-09-17 13:51:15 +08:00
Zhenhuan Chen
6983e8a00d
[https://nvbugs/5517260][fix] move scaffolding contrib module's import to subdirectory (#7758) 
Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
 2025-09-17 11:36:33 +08:00
amitz-nv
750d15bfaa
[https://nvbugs/5503529][fix] Change test_llmapi_example_multilora to get adapters path from cmd line to avoid downloading from HF (#7740) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-09-16 16:35:13 +08:00