Commit Graph

9 Commits

Author SHA1 Message Date
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
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
Kaiyu Xie
ab5b19e027
Update TensorRT-LLM (#2820) 2025-02-25 21:21:49 +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
c629546ce4
Update TensorRT-LLM (#2436) 2024-11-12 15:27:49 +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
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
b57221b764
Update TensorRT-LLM (#941)
* Update TensorRT-LLM

---------

Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
2024-01-23 23:22:35 +08:00