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
2,580 Commits 25 Branches 59 Tags 2.1 GiB
release/1.1.0rc2
Commit Graph

565 Commits

Author SHA1 Message Date
Tailing Yuan
85b4a6808d
Refactor: move DeepEP from Docker images to wheel building (#5534) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-07-07 22:57:03 +09:00
Daniel Cámpora
1260e2f33f
feat: Optimize TRTLLM Sampler perf single beam single step (#5550) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-07-07 15:44:47 +02:00
DylanChen-NV
5ca2b9bb15
[TRTLLM-5812][feat] support FP8 row-wise dense GEMM in torch flow (#5615) 
Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
 2025-07-07 18:04:57 +08:00
ChristinaZ
12d8c7d129
Refactor the topk parallelization part for the routing kernels (#5567) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-07-07 15:53:25 +08:00
Daniel Stokes
ec6c7dff1a
feat: Add support for MXFP8xMXFP4 in pytorch (#5535) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-07-06 15:32:06 -07:00
Robin Kobus
ae27261094
refactor: decoding inputs (#5679) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-06 08:21:02 +02:00
Julien Debache
6bddaf6df6
chore: Improve documentation of Kv_block_array (#5765) 
Signed-off-by: Julien Debache <julien.debache@hotmail.com>
 2025-07-05 22:25:27 +02:00
jthomson04
1b588f8390
feat: KV events for sliding window attention (#5580) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2025-07-05 06:05:20 +08:00
Stefan Niebler
d1112aac37
[TRTLLM-3442] feat: added beam search support to the PyTorch Workflow (#5333) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2025-07-05 01:35:13 +09:00
Chuang Zhu
ffc0b8f5da
Cache transceiver support VSWA (#5505) 
Signed-off-by: ShiXiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Co-authored-by: ShiXiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-07-05 01:18:42 +09:00
Faraz
81c0764012
Cherry pick "[NVBUG:5355009] Modify check for fuse_fp4_quant on SM120 (#5724) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
Co-authored-by: peaceh-nv <103117813+peaceh-nv@users.noreply.github.com>
 2025-07-04 16:53:20 +09:00
Robin Kobus
07f9cf1519
fix: Improve chunking test and skip empty kernel calls (#5710) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-04 09:08:15 +02:00
Yuan Tong
32b244af38
feat: reduce unnecessary kernel generation (#5476) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-07-04 14:37:49 +08:00
Netanel Haber
134b2383ff
[fix: nvbugs/5355493] Correctly clamp max sequence len to max attention window (#5720) 
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
 2025-07-04 08:16:25 +02:00
Robin Kobus
1a3bd140ed
chore: Remove unused isFullContextRequest method (#5666) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-03 15:08:09 +02:00
WeiHaocheng
dccbfc8b1e
fix: Set init value for moe expert id (#5660) 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
 2025-07-03 07:05:31 -04:00
Jhao-Ting Chen
77082cde38
[https://nvbugspro.nvidia.com/bug/5329655] [feat] Pytorch path add spec dec param to attention op (#5146) 
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
 2025-07-02 04:54:43 -04:00
Robin Kobus
4cd8543d8c
[TRTLLM-1316] refactor: Remove unnecessary pipeline parallelism logic from postProcessRequest (#5489) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-02 10:13:31 +02:00
qixiang-99
ca7b6ec8d8
Feat/pytorch vswa kvcachemanager (#5151) 
Signed-off-by: qixiang-99 <203170375+qixiang-99@users.noreply.github.com>
 2025-07-02 15:58:00 +08:00
Xiaowei Wang
32dfdfba30
feat: fuse w4a8 moe pre-quant scale on Hopper (#5613) 
Signed-off-by: Xiaowei Wang <100599594+xiaoweiw-nv@users.noreply.github.com>
 2025-07-01 23:02:41 -04:00
Void
7992869798
perf: better heuristic for allreduce (#5432) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-07-01 22:56:06 -04:00
liji-nv
c345f5876c
[feat] Support torch compile for attention dp (#5086) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-07-01 13:48:52 -04:00
Robin Kobus
d68fa728d8
refactor: Clean up DecodingInput and DecodingOutput (#5617) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-01 14:31:42 +02:00
Yan Chunwei
a5eff139f1
[TRTLLM-5277] chore: refine llmapi examples for 1.0 (part1) (#5431) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Co-authored-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-07-01 19:06:41 +08:00
danielafrimi
7a617ad1fe
feat: W4A16 GEMM (#4232) 
Signed-off-by: Daniel Afrimi <danielafrimi8@gmail.com>
 2025-07-01 10:36:05 +03:00
Li Min
16fc99391f
refactor: [TRTLLM-6150] Refactor moe permute and finalize op by removing duplicated code (#5557) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
 2025-06-30 08:48:04 -07:00
Robin Kobus
9bdc5951f8
refactor: decoder state setup (#5093) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-30 11:09:43 +02:00
WeiHaocheng
42a9385d02
[TRTLLM-5331] perf: Replace allgaher with AllToAllPrepare (#5570) 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
 2025-06-30 13:06:09 +08:00
Cheng Hang
64db7d27f6
[feat] Optimizations on weight-only batched gemv kernel (#5420) 
Signed-off-by: Cheng Hang <chang@nvidia.com>
 2025-06-30 10:20:16 +08:00
Enwei Zhu
b4dab23e7b
[TRTLLM-5965] perf: Optimize MoE sort kernels for large-scale EP (#5435) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-06-30 01:02:07 +08:00
Li Min
6021a439ab
Make moe permute and final as custom op (#5412) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
 2025-06-27 15:48:33 -07:00
Daniel Stokes
5773cfdcf2
feat: Add support for per expert activation scaling factors (#5013) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-06-28 09:10:35 +12:00
Robin Kobus
a8141a4513
refactor: Speculative decoding buffers part 2 (#5316) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-27 17:41:48 +02:00
Aurelien Chartier
833c0dea4a
[TRTLLM-6104] feat: add request_perf_metrics to LLMAPI (#5497) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-06-27 17:03:05 +02:00
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
peaceh-nv
cb58073ab7
Fix : fix build for sm120 (#5265) 
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
 2025-06-27 20:42:47 +08:00
ChristinaZ
a608b00d38
Fix mPtrExpertCounts allocation in MoE TRT-LLM backend (nvfp4) (#5519) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-06-27 20:17:40 +08:00
Daniel Stokes
83a1f60556
feat: Expose bias and FP8_MXFP4 MOE CUTLASS backend features to pytorch (#5410) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-06-27 12:29:34 +08:00
Tailing Yuan
ef43b95aa1
Fix execute_process: check results using EQUAL (#5481) 2025-06-27 11:57:04 +08:00
Anthony Chang
de7cd0de05
fix: MoE autotune fallback failed to query default heuristic (#5520) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-06-26 17:28:48 +01:00
jmydurant
8836990bde
[TRTLLM-3602][feat] support nvfp4 model and fp8 kv cache for MLA chunked prefill (Blackwell) (#5475) 
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2025-06-26 22:18:08 +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
Bo Li
1bab9000a6
perf: Optimize swizzle_sf, unswizzle_sf, reswizzle_sf (#5318) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-06-26 14:03:56 +08:00
Alessio Netti
7e681fbe52
[chore] Allow configuring linking of NVRTC wrapper (#5189) 
Signed-off-by: Alessio Netti <netti.alessio@gmail.com>
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-26 07:26:10 +02:00
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
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
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
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
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
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
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
Fanrong Li
5d4ab47d5b
fix: refactor and fix mtp vanilla (#4762) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-06-20 05:23:39 +08:00
Kaiyu Xie
113f6fbadd
Fix: missing clientId when serialize and deserialize response (#5231) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-06-19 23:05:11 +08:00
Fanrong Li
c7af650d5a
Fix: fix the deterministic issue in the MTP Eagle path (#5285) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-06-19 18:08:40 +08:00
yunruis
b3e886074e
Fix CI build time increase (#5337) 
Signed-off-by: yunruis <205571022+yunruis@users.noreply.github.com>
 2025-06-19 13:49:42 +08:00
jellysnack
0623ffe3bc
feat: Add LLGuidance Support for PyTorch Backend (#5214) 
Signed-off-by: jellysnack <oleg.jellysnack@gmail.com>
Signed-off-by: jellysnack <158609015+jellysnack@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-06-18 19:33:34 +08:00
Bo Li
d76bda7f2c
chore: Refine printed info of CHECK_TYPE. (#5295) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-06-18 15:35:41 +08:00
Yukun He
6711ad9cf3
[TRTLLM-5589] feat: Minor optimizations for tunable FP8 batched GEMM op. (#5139) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-06-18 14:33:46 +08:00
Robin Kobus
627062c265
refactor: Update decoder buffer and logits management (#4450) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-18 08:10:32 +08:00
qsang-nv
5236bb9084
delete cubins (#5274) 
Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
 2025-06-17 22:10:49 +08:00
QI JUN
f899c4d294
Re-implement LlmResponse in Python to reduce host overhead of pybind (#5224) 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-06-17 21:28:09 +08:00
Dom Brown
44fb3c1673
[TRTLLM-5770] feat: Integrate TRT-LLM Gen FP8 block scale MoE with Pytorch workflow kernel autotuner (#5207) 
- Adds a new Python custom op (fp8_block_scale_moe_runner) and a FP8BlockScaleMoERunner class for autotuning.
- Updates C++ MoE and batched GEMM kernels to accept a configIndex for workspace sizing and execution.
- Extends the unit test to run both autotuned and non-autotuned code paths.

Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-06-17 21:01:56 +08:00
amirkl94
8451a87742
chore: Mass integration of release/0.20 (#5082) 
Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Co-authored-by: Erin <14718778+hchings@users.noreply.github.com>
Co-authored-by: Frank <3429989+FrankD412@users.noreply.github.com>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Co-authored-by: Yechan Kim <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
 2025-06-17 14:32:02 +03:00
liji-nv
13eef642e6
[feat] Piecewise cuda graph support for MLA (#4467) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-06-17 18:58:38 +08:00
Robin Kobus
dc3861b4aa
refactor: Unify decoder test with e2e worklfow (#5239) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-17 12:04:58 +02:00
qsang-nv
faca19c2f0
update setup.py for special cases (#5227) 
Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
 2025-06-17 16:41:07 +08:00
qsang-nv
134cb66a53
fix mla test (#5240) 
Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
 2025-06-17 15:26:25 +08:00
Enwei Zhu
4b82b8b4c7
[TRTLLM-5330] perf: Optimize MoE supplementary kernels for large-scale EP (#5215) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-06-17 15:23:24 +08:00
Tracin
a2e8ae1120
Update internal cutlass commit. (#5228) 
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
 2025-06-17 10:47:45 +08:00
Robin Kobus
b6ca677741
refactor: remove decoder request from decoder interface (#5129) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-16 09:12:30 +02:00
Anthony Chang
4f9fa9f21d
feat: MoE trtllm backend kernel update (#5183) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-06-16 14:46:13 +08:00
Chuang Zhu
1d2b0d3d80
use file lock to avoid port conflict (#5123) 2025-06-16 14:15:37 +08:00
Robin Kobus
dda64166cd
refactor: Scheduling based on KV cache state (#4865) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-16 08:14:58 +02:00
Tracin
ef3fdc8051
feat: Add w4a8_mxfp4_fp8 quantization recipe. (#4867) 
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
 2025-06-16 11:30:57 +08:00
qsang-nv
5a01ba5260
use cu for fmha_v2 (#4694) 
Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
 2025-06-15 18:40:44 +08:00
Aurelien Chartier
1389f5a4d3
feat: Add support for fp8 rowwise quantization (#4876) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
Co-authored-by: aikitoria <151776613+aikitoria@users.noreply.github.com>
 2025-06-14 06:37:48 -07:00
Robin Kobus
443b2eb51f
refactor: Speculative decoding buffers (#5091) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-14 11:39:32 +02:00
yunruis
b99c5ce8c1
Feat/ds r1 min latency opt round3, add router gemm, fused a gemm, PDL (#4560) 
Signed-off-by: yunruis <yunruis@nvidia.com>
Signed-off-by: kduan <176893526+Kefeng-Duan@users.noreply.github.com>
Signed-off-by: Kefeng-Duan <176893526+Kefeng-Duan@users.noreply.github.com>
Co-authored-by: kduan <176893526+Kefeng-Duan@users.noreply.github.com>
 2025-06-14 17:36:22 +08:00
dongxuy04
97657bfda2
optimize memset before alltoall communication (#5188) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-06-14 10:49:47 +08:00
Perkz Zheng
3d87770e15
[https://nvbugspro.nvidia.com/bug/5295470] support headDim 256 for blackwell fmha kernels (#5164) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-06-13 23:01:01 +08:00
Chuang Zhu
8e9937081d
ucxx only use ucp_feature_tag to aviod some issuse on some platform (#4994) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-06-13 19:14:25 +08:00
yunruis
e5be3a95b3
fix: fix license bug (#5200) 
Signed-off-by: yunruis <205571022+yunruis@users.noreply.github.com>
 2025-06-13 18:58:15 +08:00
yunruis
30c5b4183a
refactoring: port customized kernels with public cutlass version (#5027) 
Signed-off-by: yunruis 

Merge this to unblock others since the full CI has been run through
 2025-06-13 16:19:31 +08:00
Yao Yao
12e075eb70
[nvbug 5333996 ][fix] Unload XQA cubins early to avoid static lifetime (#5133) 
Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com>
 2025-06-13 15:53:29 +08:00
Matthias Jouanneaux
514baf1287
[fix] Fix comment to pass guardwords check (#5191) 
Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com>
 2025-06-13 15:49:59 +08:00
zhhuang-nv
a891013e3c
[feat] Optimize KV Cache Reuse for MLA (#4869) 
Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
 2025-06-13 11:03:05 +08:00
Matthias Jouanneaux
a0b6c635b1
[feat] trtllmGen MoE routing: added support for top groups and top K bounds (#4063) 
Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com>
Co-authored-by: hlu1 <14827759+hlu1@users.noreply.github.com>
Co-authored-by: Nikita Korobov <14355239+nekorobov@users.noreply.github.com>
 2025-06-13 06:00:02 +08:00
Xiaodong (Vincent) Huang
cc2a1344be
None: fix OOM because of unnecessary mha workspace (#5056) 
Signed-off-by: Vincent Huang <vincenth@nvidia.com>
 2025-06-12 21:56:05 +02:00
liji-nv
10ab9791ec
[fix] Do not reuse dummy request KVCache (#4804) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-06-12 15:24:50 +08:00
Netanel Haber
e692779ead
Solve underallocation in VSWA+/VGQA (#4667) 
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2025-06-12 12:12:46 +08:00
HuiGao-NV
43192379af
Use backend to replace macro to control enablement of MNNVL all reduce (#4635) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-12 11:22:49 +08:00
Zheng Duan
ee44fa00f8
chore: rename IOFormatter to BaseCacheFormatter (#5068) 
Signed-off-by: Zheng Duan <200704041+zhengd-nv@users.noreply.github.com>
 2025-06-12 10:50:14 +08:00
Bo Li
1b79041f5d
fix: XQA is not enabled when history_length < kMinHistoryTokensPerBlock. (#4264) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-06-11 09:38:10 +08:00
Tracin
6c91f1c7ac
Mxfp8xmxfp4 quant mode(#4978) 
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-06-10 22:01:37 +08:00
Zongfei Jing
6d1f2d0fd7
[TRTLLM-3927] [feat] Finalize + Allreduce + add + rmsnorm fusion (#4756) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-06-10 19:55:16 +08:00
Aurelien Chartier
dcf72c6ad3
chore: cleanup GDS Cmake interface (#4928) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-06-10 17:25:43 +08:00
dongxuy04
7137cc8f67
fix cuda driver link issue with driver version less than 12.3 (#5025) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-06-10 15:27:39 +08:00
pcastonguay
87c56ab024
perf: Removing initializing ptuning buffers to zero (#4915) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-06-09 21:57:21 -04:00
Daniel Cámpora
d68b8180d3
feat: port MakeDecodingBatchInputOutput to python in TRTLLMSampler (#4828) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-06-10 07:28:34 +08:00
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
Dom Brown
9c012d5bf8
[TRTLLM-5589] feat: Integrate TRT-LLM Gen FP8 Batched GEMM with Pytorch workflow kernel autotuner (#4872) 
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-06-09 11:02:48 +01:00
liji-nv
1d4f748773
[fix] Fix illegal mem access and possible accuracy lose. Cherry-pick … (#5017) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-06-09 17:50:57 +08:00
ChristinaZ
f45aff2b7d
Add customized renormalized moe routing kernel for moe cutlass backend (#4955) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-06-09 17:38:50 +08:00
Chuang Zhu
9a874760c1
Kv cache transfer support duplicate heads (#4929) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-06-09 14:11:19 +08:00
Chuang Zhu
947571c311
Fix buffer count (#5007) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-06-09 14:01:13 +08:00
Daniel Stokes
3a4851b7c3
feat: Add Mixture of Experts FP8xMXFP4 support (#4750) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-06-09 13:25:04 +08:00
Omer Ullman Argov
8731f5f14f
chore: Mass integration of release/0.20 (#4898) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Hui Gao <huig@nvidia.com>
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: Ruodi <200874449+ruodil@users.noreply.github.com>
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
Signed-off-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
Signed-off-by: moraxu <mguzek@nvidia.com>
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Yiqing Yan <yiqingy@nvidia.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Co-authored-by: HuiGao-NV <huig@nvidia.com>
Co-authored-by: brb-nv <169953907+brb-nv@users.noreply.github.com>
Co-authored-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: ruodil <200874449+ruodil@users.noreply.github.com>
Co-authored-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
Co-authored-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
Co-authored-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
Co-authored-by: xinhe-nv <200704525+xinhe-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: Larry <197874197+LarryXFly@users.noreply.github.com>
Co-authored-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Yechan Kim <161688079+yechank-nvidia@users.noreply.github.com>
 2025-06-08 23:26:26 +08:00
dongxuy04
1e369658f1
feat: large-scale EP(part 6: Online EP load balancer integration for GB200 nvfp4) (#4818) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
Signed-off-by: ShiXiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Co-authored-by: ShiXiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-06-08 10:25:18 +08:00
Jinyang Yuan
20d0649f19
[feat] Support XQA-based MLA on SM120 (#4858) 
Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com>
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
Co-authored-by: Yao Yao <lowsfer@users.noreply.github.com>
Co-authored-by: peaceh-nv <103117813+peaceh-nv@users.noreply.github.com>
 2025-06-06 22:32:49 +08:00
Anthony Chang
eeb555e37b
chore: memoize weight shuffle index to speed up weight preproc in moe_backend=TRTLLM (#4826) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-06-06 16:13:54 +08:00
dongjiyingdjy
51652b9b2b
feat : add PositionEmbeddingType=0 to xqa support (#4934) 
Signed-off-by: Jiying Dong <87510204+dongjiyingdjy@users.noreply.github.com>
 2025-06-05 21:50:42 +08:00
Shiyu Li
b0d287c9b7
[TRTLLM-4647][fix] Fix the no fusion allreduce hanging (#4594) 
Signed-off-by: Shiyu Li <shili@nvidia.com>
 2025-06-04 18:26:13 -07:00
Omer Ullman Argov
e71de2a13e
chore: Mass integration of release/0.20. (#4871) 
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Omer Ullman Argov <118735753+omera-nv@users.noreply.github.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
 2025-06-04 14:12:27 +08:00
Zheng Duan
ded694b1aa
feat: cache reuse support (selective cache transfer) in mla cache formatter (#4749) 
Signed-off-by: Zheng Duan <200704041+zhengd-nv@users.noreply.github.com>
 2025-06-04 09:56:31 +08:00
ChristinaZ
d64af85e8c
Replace memset with data initialization within kernels (#4851) 
Signed-off-by: Christina Zhang <christinaz@nvidia.com>
 2025-06-04 08:56:46 +08:00
Perkz Zheng
a089aa3225
[https://nvbugspro.nvidia.com/bug/5300080] Fix the bug of setting attention_chunk_size and enable chunked-attention in the generation-phase by default (#4693) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-06-03 19:02:57 -04:00
Nikita Korobov
8043d7a03c
feat: update DeepSeek FP8 TRT-LLM Gen cubins (#4643) 
Signed-off-by: Nikita Korobov <nkorobov@nvidia.com>
 2025-06-03 14:07:54 -07:00
Robin Kobus
3de02582dd
refactor: Separate DecoderState from GptDecoderBatched (#4700) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-06-03 09:42:01 +02:00
Robin Kobus
b9263a8e10
fix: max_num_sequences calculation with overlap scheduling (#4532) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Co-authored-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-06-03 09:31:22 +02:00
Tian Zheng
9832787050
[feat] Enable NVFP4 output for TRTLLM attention kernels (#4737) 
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
 2025-06-03 10:00:17 +08:00
Yilin Fan
90aab0596e
[fix] Fix Llama4 guradwords failures (#4844) 
Signed-off-by: Yilin Fan <206948969+nv-yilinf@users.noreply.github.com>
 2025-06-02 13:43:42 -07:00
Enwei Zhu
5b4852b7b5
feat: large-scale EP(part 5: Static EP load balancer with offline statistics) (#4695) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-06-02 01:25:02 +08:00
Netanel Haber
2ce05c3ab4
'entered copyBlock' format string expects %s, pass string rather than int (#4820) 
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2025-06-01 08:54:33 -07:00
tomeras91
bf9cd11fd4
[TRTLLM-4783][feat] Mamba2 kernel updates for Nemotron-H (#4494) 
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
 2025-06-01 13:56:44 +03:00
Daniel Cámpora
69c7fe8905
[TRTLLM-4987][feat] Partial support of context logits in TRTLLMSampler (#4538) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-06-01 03:32:43 +08:00
Enwei Zhu
25dde49c28
fix: EP load balancer with MTP layer and route offset by EP rank (#4767) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-06-01 00:07:44 +08:00
Chuang Zhu
f117d6abe9
Fabric Memory for KV Cache Transfer (#4717) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-05-30 15:50:21 +08:00
Thor Johnsen
55d56f8155
[JIRA-5226219][fix] Fix Bug in KV cache manager (#4596) 
Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>
 2025-05-29 22:03:20 -07:00
Jinyang Yuan
5339d367ce
[perf] Reduce the workspace size of FP4 activation scales for MoE (#4303) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-05-30 09:03:52 +08:00
Yilin Fan
31bb650298
Cherry pick feat/llama4 to main (#4739) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
Signed-off-by: Yilin Fan <206948969+nv-yilinf@users.noreply.github.com>
Co-authored-by: Chenfei Zhang <chenfeiz@nvidia.com>
 2025-05-30 05:28:40 +08:00
Robin Kobus
79a94a28f9
refactor: unique_ptr instead of shared_ptr (#4697) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-29 22:49:35 +02:00
Jhao-Ting Chen
fcadce9f8d
[fix] Eagle-2 LLMAPI pybind argument fix. (#3967) 
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-05-29 12:23:25 -07:00
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
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
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
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
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
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
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
Perkz Zheng
4d711be8f4
Feat: add sliding-window-attention generation-phase kernels on Blackwell (#4564) 
* move cubins to LFS

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

* update cubins

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

* add sliding-window-attention generation-phase kernels on Blackwell

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

* address comments

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

---------

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-05-26 09:06:33 +08:00
shaharmor98
2b8f6d2871
Fix snake case format (#4559) 
fix snake case format

Signed-off-by: Shahar Mor <17088876+shaharmor98@users.noreply.github.com>
 2025-05-25 17:57:17 +08:00
Chuang Zhu
b60846b47d
fix datatype check (#4606) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-05-24 08:36:17 +08:00
Yao Yao
ef763b0ddc
fix: rename some terms (#4534) 
Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com>
 2025-05-23 23:23:49 +08:00
Robin Kobus
7b2818a47b
refactor: CreateNewDecoderRequests (#4452) 
* refactor: CreateNewDecoderRequests

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

* refactor: Consolidate request generation in CreateNewDecoderRequests

- Removed the GenerateRequestOptions class and integrated its functionality into CreateNewDecoderRequests.
- Updated the constructor of CreateNewDecoderRequests to accept parameters for speculative decoding and normalization options.
- Modified the operator() method to handle request generation directly, improving code organization and reducing redundancy.
- Cleaned up associated includes and references throughout the codebase.

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

* refactor: Simplify request handling in CreateNewDecoderRequests

- Removed the generateRequestOptions method and integrated its logic directly into the operator() method.
- Updated the request generation process to improve clarity and reduce redundancy.
- Adjusted the return type to streamline the handling of batch slots, decoder requests, and sampling configurations.

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

* refactor: Enhance createDecoderRequests method in CreateNewDecoderRequests

- Updated the createDecoderRequests method to include additional parameters for decoder state and CUDA streams, improving flexibility in request handling.
- Removed redundant request generation logic from the operator() method, streamlining the process.
- Adjusted the newRequest method to utilize the updated decoder request structure, enhancing clarity and maintainability.

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

* refactor: Use MedusaBuffers instead of RuntimeBuffers in CreateNewDecoderRequests

- Updated references from RuntimeBuffers to MedusaBuffers across the CreateNewDecoderRequests class and its methods, enhancing clarity in buffer management.
- Adjusted method signatures and internal logic to accommodate the new MedusaBuffers type, ensuring compatibility with existing functionality.
- Cleaned up unnecessary includes and improved code organization for better maintainability.

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

* refactor: Update CreateNewDecoderRequests to use DecoderState and CudaStream parameters

- Modified method signatures in CreateNewDecoderRequests to replace GptDecoderBatched with runtime::decoder::DecoderState and added a separate CudaStream for the decoder.
- Adjusted the implementation of the operator() method to accommodate the new parameters, enhancing flexibility in request handling.
- Updated associated bindings in the pybind11 interface to reflect the changes in method signatures, ensuring consistency across the codebase.

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

* refactor: Update TRTLLMSampler to use refactored create_new_decoder_requests

- Updated the sampler.py to reflect changes in the request handling logic, replacing generate_request_options with create_new_decoder_requests for improved clarity and consistency.
- Updated bindings and method signatures for decoder stream handling.

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

* refactor: Update gptDecoderBatchedTest to use CreateNewDecoderRequests::newRequest

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

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-23 22:54:37 +08:00
zhhuang-nv
8452775db8
[TRTLLM-5070][feat] Support FP8 KV Cache Reuse for MLA (#4535) 
* optimize kv cache reuse workflow for MLA

write kv cache first and only call up-projection GEMM once
relax contiguous requirements of k/v for setting paged kv cache
return two contiguous tensors when loading MLA KV Cache

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* support fp8 kv cache for MLA kv cache reuse

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* resolve comments

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

---------

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
 2025-05-23 19:47:50 +08:00
Anthony Chang
bbea2647b1
Qwen3 supports TRTLLM FP4 MoE backend (#4530) 
* MoE TRTLLM backend for Qwen3

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* add extra moe_backend to test

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* address comments

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* conditionally compile kernels on newer archs

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* missing positional arg

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* Update the routing kernels

Signed-off-by: Christina Zhang <christinaz@nvidia.com>

* Revise usage of TLLM_LOG_ERROR

Signed-off-by: Christina Zhang <christinaz@nvidia.com>

* Add unit test for Qwen3 moe (trtllm_gen backend)

Signed-off-by: Christina Zhang <christinaz@nvidia.com>

* improve weight processing speed of moe_backend=TRTLLM; roughly 2x

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* tidy and minor fix

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* temporarily disable accuracy test that has known issue

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

---------

Signed-off-by: Anthony Chang <anchengc@nvidia.com>
Signed-off-by: Christina Zhang <christinaz@nvidia.com>
Co-authored-by: Christina Zhang <christinaz@nvidia.com>
 2025-05-23 18:31:08 +08:00
Bo Li
9ae705af1b
perf: Add fused q_norm/k_norm/RoPE for Qwen3. (#4482) 
* Add Julien's origina kernel.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Get rid of UpdateKVCache functionality.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Add kernels.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Add torch OP.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Update cmake.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Torch OP must use double as argument dtype.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Add unittest.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Add unittest.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Fix misaligned access when head_dim=64.
In this case, numElemsPerThread=2, numVecPerThread=0. But the store code incorrectly perform vectorized store, some threads (e.g., lane1) issue store to address that is not aligned to 64 bit.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Remove unroll (compiler can do that).
Cleanup code.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Add switch for interleave.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Refactor vectorized load/store.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Implement is_neox. Result not correct yet.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Fix is_neox=True.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

* Add q_weight and k_weight.

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>

---------

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-05-23 15:31:04 +08:00
CarstyYou
ef280e687e
[feat] support fp8 blockscale gemm on sm89 (#4481) 
* [feat] integrate ada blockwise gemm

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [fix] align scale M

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [feat] swizzle mma output

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [test] add ut for sm89

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [delete] remove useless comments

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [chore] codestyle

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [fix] fix review comments

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [chore] fix license

Signed-off-by: CarstyYou <xiy@nvidia.com>

* [chore] fix license

Signed-off-by: CarstyYou <xiy@nvidia.com>

---------

Signed-off-by: CarstyYou <xiy@nvidia.com>
Co-authored-by: bhsueh_NV <11360707+byshiue@users.noreply.github.com>
 2025-05-23 10:39:10 +08:00
nv-guomingz
e3a534d0ee
chore: guardword clean for header file. (#4540) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-05-23 10:08:14 +08:00
pcastonguay
d7d455e7ea
[feat][TRTLLM-5018] Dis serving python runtime trt backend (#4243) 
* feat: Enabling dis serving with TRT backend with Python runtime

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>

* Fixing formatting

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>

* Fixing disagg mtp test

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>

---------

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-05-22 22:01:06 -04:00
dongxuy04
338744fba6
fix[nvbug-5295425]: [TRTLLM-5385] fix race condition in MoeLoadBalancer (#4573) 
fix moe possible race cond and add bypass worker thread for no updates

Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-05-23 09:24:23 +08:00
nv-guomingz
3549b68c1c
chroe:clean useless flag (#4567) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-05-23 07:05:15 +08:00
Mike Iovine
9c0de251db
[feat] Integrate Hopper chunked attention kernels (#4330) 
* Integrate chunked attention kernels

Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>

* Fix cache key

Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>

* Fix lint

Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>

---------

Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-05-22 17:10:57 -04:00
Chuang Zhu
558eaecf16
fix sequence data race (#4565) 
stash for debug broken promise

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-05-22 23:13:48 +08:00
Chuang Zhu
44cfd757b2
Agent interface impl for NIXL (#4125) 
* agentConnection

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

recv

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

agentState

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

NIXL interfaces

Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>

update cmakelists

Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>

nixl improve

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

remove cppzmq

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

fix

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

transferAgent remove register

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

work for cache Test

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

reduce sleep time

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

fix test

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

intergarte

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

nixl env

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

fix rebase error

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

cpp test

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

stash for send metaData

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

loadRemoteMD after fetchRemoteMD

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

workaround for mixed gen and context

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

test_env

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

avoid port conflict in test

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* format

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* use std::string

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* typo

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* fix transferAgentTest

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

---------

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-05-22 09:09:41 +08:00
Nikita Korobov
e1b42be3d1
fix: TRT-LLM Gen dtype declaration (#4503) 
Signed-off-by: Nikita Korobov <nkorobov@nvidia.com>
 2025-05-21 23:56:37 +02:00
Zongfei Jing
dbaddb3a29
Adding two-shot allreduce kernel and mnnvl multicasting buffer (#4216) 
* Adding two-shot allreduce kernel and mnnvl multicasting buffergit gffe

Signed-off-by: Shiyu Li <shili@nvidia.com>

Adding comments

Signed-off-by: Shiyu Li <shili@nvidia.com>

Add unittest of the twoshot kernel.

Signed-off-by: Shiyu Li <shili@nvidia.com>

Update dispatch logic

Signed-off-by: Shiyu Li <shili@nvidia.com>

Use cpu barrier instead of GPU at init

Signed-off-by: Shiyu Li <shili@nvidia.com>

Merge dispatch logic fix

Signed-off-by: Shiyu Li <shili@nvidia.com>

Update the kernel to use GPU-managed buffer

Signed-off-by: Shiyu Li <shili@nvidia.com>

* Refine

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Clean code

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Fix compile error

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Fix issue

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Clean up

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Simplify AllReduce interface

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Rename

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Fix warning

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Tidy code

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Rename

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Fix compile error

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Refine

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Skip ut for no_fusion

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Refine

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

---------

Signed-off-by: Shiyu Li <shili@nvidia.com>
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
Co-authored-by: Shiyu Li <shili@nvidia.com>
 2025-05-22 03:42:36 +08:00
Ruoqian Guo
db7446fda7
Feat: add deep_gemm swapab Kernel (#4430) 
* feat: add deepgemm_swapab

feat: add fp8_gemm_kernel_swapab

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>

feat: set threshold for deepgemm and deepgemmswapab

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>

* docs: update README.md

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>

* fix: std::runtime_error needs #include <stdexcept>

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>

* chores: remove the redundant code

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>

* feat: support for dense deep_gemm swapab

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>

* chores: remove redundant code

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>

---------

Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com>
Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
 2025-05-21 10:48:43 +08:00
Thor Johnsen
5d438be59a
[TRTLLM-5000][feat] Pytorch implementation of ngram drafter (#3936) 
* v1.5

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

v1.5.4 Add back draft_overhead to spec dec stats

Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>

* v1.5.5: fix CI error

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* v1.6: fix CI error 8196 > 8192

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* Address reviewer concerns

Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>

* Address reviewer concerns

Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>

* precommit run

Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>

* v2.0: Address reviewer concerns

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* v2.1: add fix from wili

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* Revert changes that require use of TypeAlias because that requires python version >= 3.10

Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>

---------

Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>
Co-authored-by: wili-65535 <wili-65535@users.noreply.github.com>
 2025-05-21 10:40:00 +08:00
Perkz Zheng
426f6fd2bc
Feat: add chunked-attention kernels on Blackwell (#4394) 
* update cubins

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

* add chunked-attention kernels on blackwell

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

fix

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

---------

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-05-21 10:16:46 +08:00
djns99
a030a898d1
perf: Fuse gemm setup function for SM90/SM100 MOE plugin path (#4146) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-05-21 10:00:36 +08:00
Robin Kobus
8564c5a41f
refactor: Unify request order in TRT and PyTorch workflow (#4096) 
* chore: Partition context requests in MicroBatchScheduler

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

* fixup! chore: Partition context requests in MicroBatchScheduler

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

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-20 18:49:27 +02:00
dongxuy04
21aff2e313
feat: large-scale EP(part 2: MoE Load Balancer - core utilities) (#4384) 
* first commit of cpp moe loadbalance code

Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>

* add python bindings for moe load balance

Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>

* add python wrapper, ut and bug fixes

Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>

* add binding for layerId and update binding test

Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>

* add host tensor sharing and ut

Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>

---------

Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-05-20 17:53:48 +08:00
kanghui0204
6f3922f318
feat: Low Precision Allreduce for PCIe based GPU (#4344) 
This PR adds a customized allreduce to TensorRT-LLM. The new allreduce is used for communication on PCIe-based GPUs via low-precision quantization, which can accelerate the PCIe allreduce process.

Signed-off-by: Hui Kang <hkang@nvidia.com>
Co-authored-by: Hui Kang <hkang@nvidia.com>
 2025-05-20 06:53:46 +08:00
Yuxian Qiu
c8e062bfd3
fix: [nvbugs/5287097] Align PP layer distribution between pytorch and TRT flow. (#4399) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
Co-authored-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-05-19 14:25:36 -07:00
Perkz Zheng
1c5b0d6a13
[Feat] add chunked-attention kernels on Hopper (for llama4) (#4291) 
* update cubins

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

* add mtp for fmha_v2 MLA kernels and add chunked-attention support for hopper fmha kernels

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

---------

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
 2025-05-19 09:57:10 -07:00
Faraz
7656af1b57
[TRTLLM-4618][feat] Fix cutlass MoE GEMM fallback failure on FP8 + add e2e test for Mixtral 8x7B FP8 on RTX6000 Pro (SM120) (#4335) 
* add mixtral7x8b fp8 test with fixed cutlass fp8 moe gemm

Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>

* update cutlass versions

Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>

* added internal cutlass with fix and docker update

Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>

* added mixtral to pro 6000

Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>

---------

Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
 2025-05-19 08:56:21 -07:00
liji-nv
58e405624a
[https://nvbugs/5123103][fix] Fix torch compile for DeepSeekV3 (#3952) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-05-19 22:12:25 +08:00
Shi Xiaowei
df2798e0c3
feat: NIXL interface integration (#3934) 
NIXL interfaces

Signed-off-by: ShiXiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-05-19 18:18:22 +08:00
Void
62bb7f9286
fix potential issues in allreduce fusion kernel and ut (#4226) 
fix allreduce fuison kernels and ut

Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>

---------

Co-authored-by: AIDC-AI <AIDC-AIB@365fanyi.com>
 2025-05-19 17:38:29 +08:00
Jinyang Yuan
b618e1f55b
perf: Eliminate the need for attention DP padding when possible (#3439) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
Co-authored-by: raccoonliukai <raccoonliu@tencent.com>
 2025-05-17 13:30:55 +08:00
Robin Kobus
4e370a509a
refactor: Copy sequence lengths once in decoder setup (#4102) 
* refactor: Copy sequence lengths once in decoder setup

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

* refactor: Update DecoderInputBuffers to remove duplicated buffers

- Renamed and reorganized buffer variables in decoderBuffers.h and decoderBuffers.cpp for better readability.
- Adjusted references in generateRequestOptions.cpp to align with the new buffer structure.

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

* refactor: Move getEmbeddingBias to anonymous namespace

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

* refactor: Filter context requests

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

* refactor: GenerateRequestOptions using more fine-grained functions

- Added a new method `createDecoderRequests` to encapsulate the logic for creating decoder requests from finished context requests.
- Updated the `operator()` method to utilize the new method, improving code clarity and maintainability.

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

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

* refactor: Update TRTLLMDecoder

- Updated the `generate_request_options` call.
- Updated the `make_decoding_batch_input_output` call.

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

* refactor: Remove const where we modify input buffers

- Changed `DecoderInputBuffers` parameters from const references to non-const references in multiple functions to allow modifications.
- Updated related function calls to ensure compatibility with the new parameter types.

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

* fixup! refactor: Copy sequence lengths once in decoder setup

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

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-16 22:03:55 +08:00
Nikita Korobov
fa3879629e
feat: TRT-LLM Gen integration for BMM and MoE refactoring (#4280) 
- Adds BatchedGemm cubins and the respective call interface from TensorRT-LLM Generator. 
- Refactors TRT-LLM Gen MoE runner to call to BMM interface
- The accuracy is verified for DeepSeek R1 FP4 

Signed-off-by: Nikita Korobov <nkorobov@nvidia.com>
 2025-05-16 13:31:53 +02:00
ixlmar
f7ad49bb9b
chore: improve log-level setting UX (#4352) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-05-16 09:47:44 +01:00
NVJiangShao
6cc3f2093a
Fix bias shape in weightOnlyGroupwiseQuantMatmulPlugin for TRT workflow (#4348) 
Signed-off-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
Co-authored-by: AIDC-AI <AIDC-AIB@365fanyi.com>
 2025-05-16 10:02:30 +08:00
Erin
c44cf34373
fix: update checks that broke medusa tests when use_py_session=True (#4339) 
fix check

Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-05-15 15:47:28 -07:00
yuxianq
4f8afe4cc6
feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism (#4034) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-16 04:16:53 +08:00
yuxianq
0e87fcc228
refactor: use x is None instead of x == None. (#4244) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-15 20:00:04 +08:00
zhhuang-nv
97bc680cd8
feat: support kv cache reuse for MLA (#3571) 
* support kv cache reuse for MLA

load compressed_kv and k_pe and do up-projection
use 192/128 head size MLA context kernel
support Blackwell and Hopper now

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* add CI test

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix: set k_pe head_num to 1 for kernel 2 and kernel 2V2

Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>

* resolve comments

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* use GPTJ style RoPE for MLA

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix rebase error and some docs

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix kv_lens

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* tiny fix

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix torch compile

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix: use normal device memory instead of pinned memory for unit test

Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>

* fix L0 tests

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix torch compile after rebase

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* resolve comments

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* resolve comments again

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

---------

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
Signed-off-by: zhhuang-nv <145532724+zhhuang-nv@users.noreply.github.com>
Co-authored-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2025-05-15 15:22:21 +08:00
Zhanrui Sun
5dc3b539ba
infra: Down the gcc toolset version from 13 to 11 (#4114) 
* Down the gcc toolset version from 13 to 11

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>

* Update rocky8 images

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>

---------

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-05-15 11:08:51 +08:00
qsang-nv
0fd59d64ab
infra: open source fmha v2 kernels (#4185) 
* add fmha repo

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* fix format

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* fix code style

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* fix header

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* fix header kernel_traits.h

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* add .gitignore file

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* add SLIDING_WINDOW_ATTENTION

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* fix style

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* fix format

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* update setup.py

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

* update build_wheel.py

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>

---------

Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
Signed-off-by: qsang-nv <200703406+qsang-nv@users.noreply.github.com>
 2025-05-15 10:56:34 +08:00
QI JUN
498ce8a056
Revert "feat: Low Precision Allreduce for PCIe based GPU" (#4340) 
Revert "feat: Low Precision Allreduce for PCIe based GPU (#3851)"

This reverts commit 5e634dd1bd.
 2025-05-15 09:52:39 +08:00
hlu1
7fb0af9320
[fix] Remove stale cublas heuristics (#4326) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com@users.noreply.github.com>
Co-authored-by: Hao Lu <14827759+hlu1@users.noreply.github.com@users.noreply.github.com>
 2025-05-14 17:35:51 -07:00
Robin Kobus
d31fefde2c
[TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow (#4092) 
* chore: Remove GptSession/V1 from TRT workflow

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

* chore: Remove stateful decoders

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

* chore: Remove GptSession buffers

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

* chore: Remove GptSession utils

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

* chore: Remove GptSession kernels

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

* chore: Remove V1 GPT models from tests

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

* chore: Remove gptSessionBenchmark from scripts and docs

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

* chore: Remove gptSession IO classes

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

* chore: Remove GptSession from test lists

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

* chore: Remove GptSession from docs

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

* chore: Remove useless encoder test

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

* chore: Remove mActualBatchSize from DecoderState

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

* chore: Remove static batching from ExecutorTest

- Updated `validateContextLogits` and `validateGenerationLogits` functions to remove the `batchingType` parameter.
- Adjusted related test functions to reflect the changes in parameter lists.
- Cleaned up the instantiation of test cases to eliminate unnecessary batchingType references.

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

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-14 23:10:04 +02:00
Robin Kobus
c67da1fbaa
fix: Eagle decoding in TRT flow (#4229) 
* fix: EagleBuffers lifetime issue

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

* refactor: Clean up Eagle kernel parameters

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

* fix: Eagle draft tokens init

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

* chore: Add check for updated sequence length in TrtGptModelInflightBatching

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

* fix: Skip check for beam search

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

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-05-14 16:10:49 +02:00
DylanChen-NV
206f82115d
[bug/5247505] fix: CP accuracy on Blackwell (#4188) 
* fix xqa params for cp

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* add test

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* add test

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* try adding B200 multi gpu test

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* add accuracy tests for cp

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

---------

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
 2025-05-14 17:40:50 +08:00
kanghui0204
5e634dd1bd
feat: Low Precision Allreduce for PCIe based GPU (#3851) 
This PR adds a customized allreduce to TensorRT-LLM. The new allreduce is used for communication on PCIe-based GPUs via low-precision quantization, which can accelerate the PCIe allreduce process.

Signed-off-by: Hui Kang <hkang@nvidia.com>
Co-authored-by: Hui Kang <hkang@nvidia.com>
 2025-05-14 16:45:43 +08:00
Barry Kang
20b42912ce
[TRTLLM-3330][feat] Support DeepSeek-R1 W4A8 on Hopper (#4123) 
Support DeepSeek-R1 W4A8 on Hopper

Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Co-authored-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
 2025-05-14 15:48:07 +08:00
Perkz Zheng
e8d7834c50
fix: [https://nvbugspro.nvidia.com/bug/5238626] illegal memory address when running llama 4 with cuda graph enabled (#4101) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-05-13 14:58:54 +08:00
pcastonguay
9643be5f20
[TRTLLM-5050][feat] Enable per-request stats with PyT backend (#4156) 
* feat: Add per-request stats support with PyT backend

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>

* Adding unit test

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>

* Fixing stats unit test

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>

* Fixing test with overlap

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>

---------

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-05-12 21:35:15 -04:00
Simeng Liu
286a789549
feat: Add heuristic for GroupRMSNorm kernel selection. (#4047) 
* feat: Add heuristic for GroupRMSNorm kernel selection.

Implements a logistic regression model to dynamically select between:
- GroupRMSNormBaseKernel: Allocates warps proportional to sum of dimensions
  (better SM occupancy in most cases)
- GroupRMSNormLargeBatch: Allocates warps proportional to max dimension
  (better block scheduling in large batch scenarios)

Selection heuristic considers batch size, allocated warps, and scheduling
efficiency on the current GPU architecture. Models for Compute Capability
9.x and 10.x are trained base on nsys kernel runtime data.
The default kernel selection is the base kernel.

The python operator group_rms_norm will use the heuristic by default.
User can pick to use the base or large batch kernels as well.

Signed-off-by: Simeng Liu <simengl@nvidia.com>

* Address the comments.

Signed-off-by: Simeng Liu <simengl@nvidia.com>

---------

Signed-off-by: Simeng Liu <simengl@nvidia.com>
 2025-05-13 08:52:53 +08:00
wili
eba3623a54
Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979) 
* feat/vbws-part4-v1.8: rebase

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* feat/vbws-part4-v1.9: fix incorrect output when using short output length

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* v1.9.1: remove useless variables

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* v1.9.2:fix incorrect output when using short output length

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* v1.9.3: rebase

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* v1.9.4: rebase

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

* v1.9.5: remove API change

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>

---------

Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>
Co-authored-by: wili-65535 <wili-65535@users.noreply.github.com>
 2025-05-12 22:32:29 +02:00
Yixin Dong
c90ebadd84
feat: Support the Structural Tag in guided decoding (#4066) 
* finish

Signed-off-by: Ubospica <ubospica@gmail.com>

* update

Signed-off-by: Ubospica <ubospica@gmail.com>

* update

Signed-off-by: Ubospica <ubospica@gmail.com>

* fix

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

* exc overlap scheduler

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

* add test

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

* fix api ref

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

---------

Signed-off-by: Ubospica <ubospica@gmail.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-05-12 17:24:50 +08:00
Perkz Zheng
3f29d2f006
Feat: support exporting softmax statistics and update the kernel-selection heuristic (#4155) 
* update cubins

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

* support exporting softmax statistics and update the kernel-selection heuristic

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>

---------

Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-05-12 15:31:46 +08:00
zhhuang-nv
0a36db0aa4
[fix] trtllm-gen mla kernel warnings (#4119) 
fix trtllm-gen mla kernel warnings

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
 2025-05-09 20:21:28 +08:00
NVJiangShao
57b2fe2019
[#4085][fix] Fix apply_per_channel_scale for extremely large input sequence length. (#4089) 
Fix apply_per_channel_scale for extremely large input seq length.

Signed-off-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
Co-authored-by: crazy-JiangDongHua <759421566@qq.com>
 2025-05-09 11:57:01 +08:00
Yi Zhang
91bf5e6a8e
[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804) 
Add Piecewise CUDA Graph Support

Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
 2025-05-09 11:04:01 +08:00