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
982 Commits 25 Branches 59 Tags 2.1 GiB
d15ceae62e
Commit Graph

51 Commits

Author SHA1 Message Date
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
Chuang Zhu
e2318756ed
cacheTransceiver buffer manager (#3798) 
* cacheTransceiver buffer manager

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

* fix args

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

* cpp kvCacheManager

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

* format

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

---------

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-04-27 11:48:15 +08:00
Zheng Duan
ae48abefc1
bind block key and hasher (#3712) 2025-04-21 18:50:57 +08:00
Netanel Haber
3c52ac098f
feat: allocate minimal blocks per window size (#3028) 
* implement variable window attention by breaking the block manager into window block managers per window size

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* revert isCyclic to be true if the min attention window is reached, not per window size

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* add explanatory comment to mCyclicThreshold

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* load correct gemma config

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* don't shadow inputLength in addSequence - it should remain the function scope input length between window size loop iterations

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix KVCacheManagerVariableWindowAttentionWithReuseTest for multiple window block managers

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* if TYPE_CHECKING

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* set temp_attention_window_inputs to None explicitly

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* set temp_attention_window_inputs to None explicitly

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* pass dtype as well

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* test_gemma variable sliding window attention

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* allot a fraction of primary/secondaryBlocks to different window size heaps, depending on the window size's total contribution to the kvcache size (i.e., including all layers)

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* remove || mEnableBlockReuse which erroneously triggers beamsearch code for cyclic variable attention window code

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* turn off request delaying for MaxUtil

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* make comments better

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* windowSizesTotalSum using std::accumulate

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix error handling of forwardAsync - forwardAsync catch-all catch cleanup code that runs terminateRequest can also fail and must be caught

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix comments

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* remove assert that kills disagg tests, since it isn't necessary

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix corrupted expression: 'isNewTask && (peftCacheManager ?' -> '(isNewTask && peftCacheManager) ?' which caused boolean algebra. Main is correct

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* add Gemma3 to SUPPORTED_HF_ARCHITECTURES

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* support Gemma3

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* finally fix test_gemma - always spread at least {} into generate_summary_cmd, never None

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* finally fix test_gemma - always spread at least {} into generate_summary_cmd, never None

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix kvfactor field for deepseek

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix comment

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix gemma-3 entries in testlist to include vswa

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* only quantize gemma2 VSWA

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

remove misleading comment

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

fix test_gemma

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix test_gemma

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix test_gemma

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* in sendRequestInfo, fromOldAllocatedBlockIds->fromOldAllocatedBlockIds, like in main

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>

* fix: disable KV cache reuse if using attention sink (#3021)

* fix: disable KV cache reuse if using attention sink

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

* fix: disable KV cache reuse if sink bubble

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

* add comment

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

---------

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

---------

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-04-17 16:04:57 +08:00
pansicheng
143edc8153
fix partialMatch (#3413) 
Signed-off-by: pansicheng <sicheng.pan.chn@gmail.com>
 2025-04-11 16:42:52 +08:00
Netanel Haber
da0b0e0ee3
fix: disable kv cache reuse when minimum window size is reached, instead of maximum window size (#2983) 
* fix variable window size reuse - disable when *min attention window* starts sliding, not max

* isPreCyclic -> isCyclic, and invert logic, for clarity

* getDecoderState()

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2025-03-24 22:49:52 +08:00
Kaiyu Xie
9b931c0f63
Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
Kaiyu Xie
77d7fe1eb2
Update TensorRT-LLM (#2849) 
* Update TensorRT-LLM

---------

Co-authored-by: aotman <chenhangatm@gmail.com>
 2025-03-04 18:44:00 +08:00
Kaiyu Xie
2ea17cdad2
Update TensorRT-LLM (#2792) 
* Update TensorRT-LLM

---------

Co-authored-by: jlee <jungmoolee@clika.io>
 2025-02-18 21:27:39 +08:00
Kaiyu Xie
e88da961c5
Update TensorRT-LLM (#2783) 2025-02-13 18:40:22 +08:00
Dan Blanaru
16d2467ea8 Update TensorRT-LLM (#2755) 
* Update TensorRT-LLM

---------

Co-authored-by: Denis Kayshev <topenkoff@gmail.com>
Co-authored-by: akhoroshev <arthoroshev@gmail.com>
Co-authored-by: Patrick Reiter Horn <patrick.horn@gmail.com>

Update
 2025-02-11 03:01:00 +00:00
Kaiyu Xie
be17881062
Update TensorRT-LLM (#2582) 2024-12-16 21:50:47 -08:00
Kaiyu Xie
aaacc9bd68
Update TensorRT-LLM (#2562) 
* Update TensorRT-LLM

---------

Co-authored-by: Starrick Liu <73152103+StarrickLiu@users.noreply.github.com>
 2024-12-11 00:31:05 -08:00
石晓伟
548b5b7310
Update TensorRT-LLM (#2532) 
* blossom-ci.yml: run vulnerability scan on blossom

* open source efb18c1256f8c9c3d47b7d0c740b83e5d5ebe0ec

---------

Co-authored-by: niukuo <6831097+niukuo@users.noreply.github.com>
Co-authored-by: pei0033 <59505847+pei0033@users.noreply.github.com>
Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2024-12-04 21:16:56 +08:00
Kaiyu Xie
535c9cc673
Update TensorRT-LLM (#2460) 2024-11-19 18:30:34 +08:00
Kaiyu Xie
c629546ce4
Update TensorRT-LLM (#2436) 2024-11-12 15:27:49 +08:00
Kaiyu Xie
b7868dd1bd
Update TensorRT-LLM (#2413) 2024-11-05 16:27:06 +08:00
Kaiyu Xie
f14d1d433c
Update TensorRT-LLM (#2389) 
* Update TensorRT-LLM

---------

Co-authored-by: Alessio Netti <netti.alessio@gmail.com>
 2024-10-29 22:24:38 +08:00
Kaiyu Xie
8681b3a4c0
open source 4dbf696ae9b74a26829d120b67ab8443d70c8e58 (#2297) 
* Update TensorRT-LLM

---------

Co-authored-by: Bhuvanesh Sridharan <bhuvanesh.sridharan@sprinklr.com>
Co-authored-by: Qingquan Song <ustcsqq@gmail.com>
 2024-10-08 12:19:19 +02:00
Dan Blanaru
48686bca3a
open source 7f370deb0090d885d7518c2b146399ba3933c004 (#2273) 
* Update TensorRT-LLM

---------
Co-authored-by: Qingquan Song <ustcsqq@gmail.com>
 2024-09-30 13:51:19 +02:00
Kaiyu Xie
78f5c2936b
Update TensorRT-LLM (#2184) 2024-09-03 12:14:23 +02:00
Kaiyu Xie
74b324f667
Update TensorRT-LLM (#2110) 2024-08-13 22:34:33 +08:00
Kaiyu Xie
be9cd719f7
Update TensorRT-LLM (#2094) 
* Update TensorRT-LLM

---------

Co-authored-by: akhoroshev <arthoroshev@gmail.com>
Co-authored-by: Fabian Joswig <fjosw@users.noreply.github.com>
Co-authored-by: Tayef Shah <tayefshah@gmail.com>
Co-authored-by: lfz941 <linfanzai941@gmail.com>
 2024-08-07 16:44:43 +08:00
Kaiyu Xie
2d234357c6
Update TensorRT-LLM (#1954) 
* Update TensorRT-LLM

---------

Co-authored-by: Altair-Alpha <62340011+Altair-Alpha@users.noreply.github.com>
 2024-07-16 15:30:25 +08:00
Kaiyu Xie
a96cccafcf
Update TensorRT-LLM (#1918) 2024-07-09 14:42:22 +08:00
石晓伟
2a115dae84
Update TensorRT-LLM (#1793) 
Co-authored-by: DreamGenX <x@dreamgen.com>
Co-authored-by: Ace-RR <78812427+Ace-RR@users.noreply.github.com>
Co-authored-by: bprus <39293131+bprus@users.noreply.github.com>
Co-authored-by: janpetrov <janpetrov@icloud.com>
 2024-06-18 18:18:23 +08:00
Kaiyu Xie
b777bd6475
Update TensorRT-LLM (#1725) 
* Update TensorRT-LLM

---------

Co-authored-by: RunningLeon <mnsheng@yeah.net>
Co-authored-by: Tlntin <TlntinDeng01@Gmail.com>
Co-authored-by: ZHENG, Zhen <zhengzhen.z@qq.com>
Co-authored-by: Pham Van Ngoan <ngoanpham1196@gmail.com>
Co-authored-by: Nathan Price <nathan@abridge.com>
Co-authored-by: Tushar Goel <tushar.goel.ml@gmail.com>
Co-authored-by: Mati <132419219+matichon-vultureprime@users.noreply.github.com>
 2024-06-04 20:26:32 +08:00
Kaiyu Xie
bf0a5afc92
Update TensorRT-LLM (#1598) 
* Update TensorRT-LLM
 2024-05-14 16:43:41 +08:00
Kaiyu Xie
06c0e9b1ec
Update TensorRT-LLM (#1530) 2024-04-30 17:19:10 +08:00
Kaiyu Xie
66ef1df492
Update TensorRT-LLM (#1492) 
* Update TensorRT-LLM

---------

Co-authored-by: Loki <lokravi@amazon.com>
 2024-04-24 14:44:22 +08:00
Kaiyu Xie
71d8d4d3dc
Update TensorRT-LLM (#1455) 2024-04-16 19:40:08 +08:00
Kaiyu Xie
035b99e0d0
Update TensorRT-LLM (#1427) 
* Update TensorRT-LLM

---------

Co-authored-by: meghagarwal <16129366+megha95@users.noreply.github.com>
 2024-04-09 17:03:34 +08:00
Kaiyu Xie
118b3d7e7b
Update TensorRT-LLM (#1387) 2024-04-01 16:39:43 +08:00
Kaiyu Xie
4bb65f216f
Update TensorRT-LLM (#1274) 
* Update TensorRT-LLM

---------

Co-authored-by: meghagarwal <16129366+megha95@users.noreply.github.com>
Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2024-03-12 18:15:52 +08:00
Kaiyu Xie
655524dd82
Update TensorRT-LLM (#1168) 
* Update TensorRT-LLM

---------

Co-authored-by: Bhuvanesh Sridharan <bhuvan.sridharan@gmail.com>
Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2024-02-27 17:37:34 +08:00
Kaiyu Xie
e06f537e08
Update TensorRT-LLM (#1019) 
* Update TensorRT-LLM

---------

Co-authored-by: erenup <ping.nie@pku.edu.cn>
Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2024-01-31 21:55:32 +08:00
Kaiyu Xie
d879430b04
Update TensorRT-LLM (#846) 
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2024-01-09 21:03:35 +08:00
Kaiyu Xie
deaae40bd7
Update TensorRT-LLM (#787) 
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2024-01-02 17:54:32 +08:00
Kaiyu Xie
d37b507f41
Update TensorRT-LLM main branch (#754) 
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2023-12-27 17:41:24 +08:00
Kaiyu Xie
a75618df24
Update TensorRT-LLM (#667) 
* Update TensorRT-LLM

---------

Co-authored-by: 0xymoro <jerrymeng100@gmail.com>
Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2023-12-15 22:14:51 +08:00
Kaiyu Xie
f7eca56161
Update TensorRT-LLM (#613) 
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Co-authored-by: zhang-ge-hao <842720660@qq.com>
 2023-12-08 17:49:24 +08:00
Kaiyu Xie
711a28d9bf
Update TensorRT-LLM (#465) 
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2023-11-24 22:12:26 +08:00
Kaiyu Xie
6755a3f077
Update TensorRT-LLM (#422) 
* Update TensorRT-LLM

---------

Co-authored-by: Tltin <TltinDeng01@gmail.com>
Co-authored-by: zhaohb <zhaohbcloud@126.com>
Co-authored-by: Bradley Heilbrun <brad@repl.it>
Co-authored-by: nqbao11 <nqbao11.01@gmail.com>
Co-authored-by: Nikhil Varghese <nikhil@bot-it.ai>
 2023-11-18 00:05:54 +08:00
Kaiyu Xie
b2fd493c16
Update TensorRT-LLM (#349) 
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2023-11-10 22:30:31 +08:00
Kaiyu Xie
f044eb8d94
Update TensorRT-LLM (#302) 
* Update TensorRT-LLM

---------

Co-authored-by: wangruohui <12756472+wangruohui@users.noreply.github.com>
 2023-11-07 19:51:58 +08:00
Kaiyu Xie
4de32a86ae
Update TensorRT-LLM (#188) 
* Update batch manager
* Update src

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Co-authored-by: jdemouth-nvidia <11447840+jdemouth-nvidia@users.noreply.github.com>
 2023-10-30 16:06:41 +08:00
Kaiyu Xie
d8b408e6dc
Update TensorRT-LLM (#148) 
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2023-10-27 12:10:00 +08:00
Kevin Xie
39d574ae66 Update 2023-10-11 00:42:09 -07:00
Kevin Xie
027cd518e3 Update 2023-10-10 23:22:17 -07:00
Kevin Xie
6e9e318e91 Update code 2023-09-28 09:00:05 -07:00