kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-16 15:55:08 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
5,121 Commits 29 Branches 68 Tags 2 GiB
2989bf5b39
Commit Graph

284 Commits

Author SHA1 Message Date
Yueh-Ting (eop) Chen
4882815fa1
[TLLM-6777][feature] Support SWA KV cache reuse OOW block detach (#7922) 
This MR is a continuation of #6768. In the previous merge request,
OOW (out-of-window) blocks are only detached when reuse is not enabled,
that is, the block movement behavior is identical between SWA and full
attention when reuse is enabled.

This merge request attempts to enable OOW block detach when reuse is
enabled. The required changes are:

- Let KV cache manager keep track of which block is used by which
  sequence
- Remove restriction for the eviction policy to be able to release a
  non-leaf block

Along with the development, bugs inside freeChildren and offload
mechanism under getFreeBlock is resolved because they will affect the
functionality this merge request is trying to achieve.

When a block goes OOW, it is released from the sequence, it will be
available to be reclaimed and the block is held by the eviction policy
for another sequence to acquire upon calling. On the other hand, we
want to potentially store the sequence for reuse. To safely achieve
this, the record of block ownership is done under
WindowBlockManager::getFreeBlock. If the block acquired was originally
owned by another sequence that is live inside the manager, then we
invalidate the sequence for store for reuse.

At the end of a sequence (when removeSequence is called toward it),
the KV cache manager will check if the sequence has all blocks not
reclaimed by another sequence. If so, then the sequence is safe to
be stored for reuse and store for reuse action will be performed.

Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-10-13 09:18:12 -07:00
Chuang Zhu
85f157f389
[None][fix] Add Lock to protect mReqeustToSession (#8085) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Co-authored-by: Xianjie Qiao <5410381+qiaoxj07@users.noreply.github.com>
 2025-10-10 21:51:50 +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
Robin Kobus
e2f69c5c23
[None] [refactor] Minor cleanup and improvements (#7619) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-10-03 11:40:06 +02:00
Yilin Fan
01423ac183
[None][feat] perf_metrics endpoint functionality improvement (#8005) 
Signed-off-by: Yilin Fan <206948969+nv-yilinf@users.noreply.github.com>
Signed-off-by: nv-yilinf <206948969+nv-yilinf@users.noreply.github.com>
 2025-10-02 17:43:25 -07:00
Patrice Castonguay
fefa7d8fa3
[None][feat] Support for cancelling requests with disaggregation (#8114) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-10-02 11:04:26 -07:00
Iman Tabrizian
33282351a2
[TRTLLM-6106][feat] Add support for KVCache transfer from KVCache reuse path (#6348) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-09-27 19:29:30 -04:00
Yueh-Ting (eop) Chen
2db22fb4e5
[None][feature] Add environment variable to adjust block pool allocation ration under kv cache manager (#7923) 
By default, we allocate equal proportion shares of memory for all
window sizes (see the else case). With TRTLLM_WINDOW_SIZE_SHARES,
we can override this behavior to adjust the memory share of each
window size. For example, if we have window size of [512, 32768],
then setting TRTLLM_WINDOW_SIZE_SHARES=0.4,0.6 will be allocating
40% of the memory to window size 512 and 60% of the memory to window
size 32768.

Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-09-26 14:09:01 +08:00
Chuang Zhu
f98fa0cf8b
[None][feat] Optimize kv cache transfer TEP (#7613) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-09-25 20:20:04 -07:00
Yueh-Ting (eop) Chen
c5012423f5
[None][chore] Remove developer name in comment (#7981) 
Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-09-25 06:43:38 -07:00
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
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
Zheng Duan
e3c1a9409f
[TRTLLM-6549][fix] add kv cache time output back (#7798) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-09-23 14:12:42 -04:00
Enwei Zhu
8330d5363a
[TRTLLM-8209][feat] Support new structural tag API (upgrade XGrammar to 0.1.25) (#7893) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-23 09:10:09 +08:00
brb-nv
8879ec4d35 [https://nvbugs/5501557][fix] Fix out-of-bounds vector access for model with multiple layer types (#7636) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
brb-nv
e10a027a03
[TRTLLM-7731][feat] KV cache transmission in disagg with CP on gen side (#7624) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-09-20 06:15:26 -07:00
Iman Tabrizian
6ce0624208
[TRTLLM-8044][refactor] Rename data -> cache for cacheTransceiver (#7659) 2025-09-16 08:43:56 -04:00
Tomer Shmilovich
ecc0e687c6
[None][feat] Nixl support for GDS (#5488) 
Signed-off-by: Tomer Shmilovich <tshmilovich@nvidia.com>
Signed-off-by: Guy Lev <glev@nvidia.com>
Co-authored-by: Guy Lev <glev@nvidia.com>
 2025-09-09 13:00:38 +08:00
Chuang Zhu
77657a1c12
[TRTLLM-7361][feat] KV cache transfer for uneven pp (#7117) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-09-08 13:37:46 -04:00
dominicshanshan
c9dca69e1b
[None][chore] Mass integration of release/1.0 - 3rd (#7519) 
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Signed-off-by: Yifei Zhang <219273404+yifeizhang-c@users.noreply.github.com>
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
Signed-off-by: Venky Ganesh <23023424+venkywonka@users.noreply.github.com>
Signed-off-by: Pamela <179191831+pamelap-nvidia@users.noreply.github.com>
Signed-off-by: Hui Gao <huig@nvidia.com>
Signed-off-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
Co-authored-by: Nave Assaf <55059536+Naveassaf@users.noreply.github.com>
Co-authored-by: Yechan Kim <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: brb-nv <169953907+brb-nv@users.noreply.github.com>
Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: Emma Qiao <qqiao@nvidia.com>
Co-authored-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Co-authored-by: Bo Deng <deemod@nvidia.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Co-authored-by: yifeizhang-c <219273404+yifeizhang-c@users.noreply.github.com>
Co-authored-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
Co-authored-by: Erin <14718778+hchings@users.noreply.github.com>
Co-authored-by: chenfeiz0326 <chenfeiz@nvidia.com>
Co-authored-by: ChristinaZ <83400082+ChristinaZ@users.noreply.github.com>
Co-authored-by: Venky <23023424+venkywonka@users.noreply.github.com>
Co-authored-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
Co-authored-by: HuiGao-NV <huig@nvidia.com>
Co-authored-by: milesial <milesial@users.noreply.github.com>
Co-authored-by: Shi Xiaowei <39303645+Shixiaowei02@users.noreply.github.com>
Co-authored-by: Michal Guzek <moraxu@users.noreply.github.com>
Co-authored-by: peaceh-nv <103117813+peaceh-nv@users.noreply.github.com>
Co-authored-by: Guoming Zhang <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Co-authored-by: pcastonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: ruodil <200874449+ruodil@users.noreply.github.com>
Co-authored-by: Linda <57756729+Linda-Stadter@users.noreply.github.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Co-authored-by: Jiagan Cheng <jiaganc@nvidia.com>
Co-authored-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
Co-authored-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-09-08 14:03:04 +08:00
Raayan Dhar
bae9560e62
[https://nvbugs/5448767][fix] sync termination of requests across PP ranks (#7455) 
Signed-off-by: raayandhar <rdhar@nvidia.com>
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Co-authored-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-09-07 08:45:49 -04:00
Chang Liu
23500b55c3
[TRTLLM-7398][feat] Support KV cache salting for secure KV cache reuse (#7106) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
 2025-09-06 17:58:32 -04:00
Shunkangz
bddf183e15
[None][feat] Add Request specific exception (#6931) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-09-04 18:43:42 -04:00
Tian Zheng
e257cb3533
[None][feat] Support NVFP4 KV Cache (#6244) 
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
 2025-09-01 09:24:52 +08:00
Richard Huo
ce580ce4f5
[None][feat] KV Cache Connector API (#7228) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
 2025-08-28 23:09:27 -04:00
qixiang-99
b165f8bc97
fix/improve kvcache allocation in PyTorch runtime (#5933) 
Signed-off-by: qixiang-99 <203170375+qixiang-99@users.noreply.github.com>
 2025-08-26 12:40:22 +08:00
Robin Kobus
37543a9ad7
[None][refactor] Simplify decoder state initialization for speculative decoding (#6869) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-08-22 18:44:17 +02:00
brb-nv
9a2b44d0f2
[None][chore] No-op changes to support context parallelism in disaggregated serving later (#7063) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-08-21 08:21:27 -07:00
Yueh-Ting (eop) Chen
020fed97b6
[TRTLLM-6341][chore] Preliminary refactors on the kv cache manager before supporting swa kv cache reuse (#6767) 
This MR is a preliminary MR for implementing the SWA reuse mechanism for
the kv cache manager. Please be aware that **no functional change is
intended** in this merge request. The purpose of the clean-up is to
decouple and remove existing functions for the up-coming SWA KV cache
reuse change to be more natural and easier to review.

Right now, (1) streamLLM, and (2) beam search with SWA, are broken. We
do not want to complicate the code base by stacking more features upon
something that does not work. This MR prunes out the logic and add
assertions so we can come back and re-support the broken feature and
remove the assertion.

Since streamLLM (sink attention) is broken now, assertion is added
under `KVCacheManager` ctor to guard for the value of
`mSinkBlockTokenLength` and `mSinkBubbleLength`. Compute logics relate
to it are pruned.

The beam search with SWA will still be broke when introducing the SWA
KV cache reuse. We will revisit this problem in the future.

On top of this, we should make an effort to update the [supporting matrix](https://github.com/NVIDIA/TensorRT-LLM/blob/feat/1.0_doc_dev/docs/source/1.0/features/feature-combination-matrix.md)
of the kv cache manager after merging the support of SWA KV cache reuse.

Changes are listed as following:
- Separate `KVCacheManager::updateToken` into `KVCacheManager::addToken`
  and `KVCacheManager::removeToken`. The functionality should be
  decoupled.
- Push utility `cacheSequenceBlockOffsets` and `cacheNewBlockOffset` from
  `KVCacheManager` down to `WindowBlockManager`. `KVCacheManager`-exposed
  functions should be real utilities that users of the structure can
  leverage. Implementation-detailed function calls should not exist at
  this level.
- Simplify "is shared last context block" logic under
  `KVCacheManager::addSequence`.

Since no functional change is intended in this merge request, no test
case is added. Several comments are added for future test coverage
reminder.

For `LlmRequestTest.ParamTest`, `streaming=True` is commented out
because we guard sink attention with assertion now.

In `capacitySchedulerTest`, `addToken` action to `crossKVCacheManager`
is removed because in encoder-decoder model, generation tokens are
added only to the decoder and not to the encoder.

Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-08-20 13:57:57 +08:00
Zero Zeng
953f4fd69e
[None][fix] acceptance rate calculation fix in benchmark_serving (#6746) 
Signed-off-by: Zero Zeng <38289304+zerollzeng@users.noreply.github.com>
 2025-08-19 17:29:36 +08:00
yifeizhang-c
4127d77678
[https://nvbugs/5394392][fix] Enlarge scheduler capacity under disagg bs == 1 (#6537) 
Signed-off-by: Yifei Zhang <219273404+yifeizhang-c@users.noreply.github.com>
 2025-08-15 09:52:06 -07:00
Robin Kobus
45c7518032
[None][refactor] Simplify decoder state initialization (#6559) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-08-12 21:44:41 +02:00
bhsueh_NV
83dbc6c75d
[TRTLLM-5532][feat] store the block of context request into kv cache (#6683) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-08-11 16:14:52 +08:00
Chuang Zhu
c566a8d2a2
[None][fix] fix same pp disagg (#6730) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-08-10 22:45:15 -04:00
Yueh-Ting (eop) Chen
199f306984
[None][chore][kv cache manager] Dead code elimination, we no longer record/fetch through WindowBlockManager:: mContextBlocksByHash (#6249) 
No functional change is intended in this MR.

`WindowBlockManager::mCachedBlocksRoot` is now who is responsible
for the bookkeeping of the `KVCacheBlock`, and the `mNextBlocks` is
now the actual hash map that fetches the block.

The `mEnableHashKey` knob and related hashing is removed.

Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-08-10 09:10:10 -04:00
Ziyi Xiong
de472828b9
[TRTLLM-6637][feat] Resolve KV cache divergence issue (#6628) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-08-09 23:15:04 +08:00
Chuang Zhu
e251f7c00b
[None][fix]revert kvcache transfer (#6709) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-08-08 07:18:53 -04:00
Zheng Duan
ebdc43e69d
[None][feat] move kv cache measure into transfer session (#6633) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-08-08 17:49:22 +08:00
Daniel Cámpora
efca359b66
[TRTLLM-6785][feat] BREAKING CHANGE Enable TRTLLM sampler by default (#6216) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-08-07 22:19:37 -04:00
pcastonguay
453a06e6ab
[TRTLLM-6881][feat] Include attention dp rank info with KV cache events (#6563) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-08-07 14:17:07 +02:00
amitz-nv
85af62184b
[TRTLLM-6683][feat] Support LoRA reload CPU cache evicted adapter (#6510) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-08-07 09:05:36 +03:00
Chuang Zhu
ee471df07c
[None][chore] optimize kv cache transfer for context TEP and gen DEP (#6657) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-08-07 11:36:05 +08:00
ixlmar
1ebceb790d
[TRTLLM-5508][feat] check input tokens + improve error handling (#5170) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-08-05 18:27:43 +01:00
Chuang Zhu
4d040b50b7
[None][chore] ucx establish connection with zmq (#6090) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-08-05 02:50:45 -04:00
Chuang Zhu
542f552d0b
use cudaSetDevice to create context ,fix nvbug 5394497 (#6403) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-08-03 13:32:55 -04:00
Robin Kobus
918fedf952
[None][refactor] Simplify finish reasons handling in DecoderState (#6524) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-08-02 07:17:43 +02:00
Jaedeok Kim
fbee279909
fix: remove duplicate layer multiplication in KV cache size calculation (#6481) 
Signed-off-by: Jaedeok Kim <jaedeokk@nvidia.com>
 2025-07-31 22:34:34 -04:00
Enwei Zhu
4b299cb77e
feat: Support structural tag in C++ runtime and upgrade xgrammar to 0.1.21 (#6408) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-07-31 09:53:52 +08:00
pcastonguay
e7ae5e2824
feat: Add support for disaggregation with pp with pytorch backend (#6369) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: raayandhar <rdhar@nvidia.com>
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Signed-off-by: pcastonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: raayandhar <rdhar@nvidia.com>
Co-authored-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-07-30 09:42:13 -04:00
Zheng Duan
c9ed1ab436
[TRTLLM-6549] chore: record delay introduced by disaggregated serving in kv cache measure (#6135) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-07-30 10:39:40 +08:00
Michal Guzek
08d57123f9
[nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974) 
Signed-off-by: moraxu <mguzek@nvidia.com>
 2025-07-25 18:10:40 -04:00
Chang Liu
7381f1dba7
[TRTLLM-5059][feat] Add KV cache reuse support for multimodal models (#5444) 
Only supports qwen in this PR
 2025-07-21 16:11:58 -07:00
amitz-nv
98428f330e
[TRTLLM-5826][feat] Support pytorch LoRA adapter eviction (#5616) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-07-20 08:00:14 +03:00
Bo Deng
0388ff9083
[https://nvbugs/5393961][fix] record kv-cache size in MLACacheFormatter (#6181) 
Signed-off-by: Bo Deng <deemod@nvidia.com>
 2025-07-19 05:06:45 +08:00
Stefan Niebler
6d7874a467
[nvbugs/5369799] fix: Update disaggregation handling in sampler (#5762) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2025-07-19 01:40:46 +08:00
Robin Kobus
ec2b953e7e
refactor: Enhanced handling of decoder requests and logits within the batch manager (#6055) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-18 12:12:08 +02:00
Iman Tabrizian
b75e53ab69
Revert "feat: nanobind bindings (#5961)" (#6160) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-07-18 10:12:54 +08:00
Linda
5bff317abf
feat: nanobind bindings (#5961) 
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
 2025-07-17 22:42:52 +08:00
Chuang Zhu
44c70c88f9
chore:[BREAKING CHANGE] use cacheTransceiverConfig as knobs for disagg service (#5234) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-07-17 17:42:07 +08:00
Zheng Duan
38db4bc7fb
feat: use session abstraction in data transceiver and cache formatter (#5611) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-07-16 13:52:44 +08:00
Robin Kobus
6d4b045d1f
refactor: Remove enforced sorted order of batch slots (#3502) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-14 17:23:02 +02:00
narutolhy
41ef1ade19
feat:enable kvcache to be reused during request generation (#4028) 
Signed-off-by: narutolhy <582909902@qq.com>
 2025-07-10 22:18:01 +09:00
xiweny
eaf8bec88b
fix: Disaggregate serving with attention DP (#4993) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
 2025-07-08 16:15:03 +08:00
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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