* Fix hang bug when KV cache is low
Signed-off-by: Iman Tabrizian <itabrizian@nvidia.com>
* Review comments
Signed-off-by: Iman Tabrizian <itabrizian@nvidia.com>
* Fix attentiondp typo
Signed-off-by: Iman Tabrizian <itabrizian@nvidia.com>
* Add CI test for this case
Signed-off-by: Iman Tabrizian <itabrizian@nvidia.com>
* fix: Fix the insertion order for responder futures
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
* fix: Fix disagg CPP
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
---------
Signed-off-by: Iman Tabrizian <itabrizian@nvidia.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
* add llama3.2 ptp test case
Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
* update test list
Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
---------
Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
* Feat: Offload ptable to cpu if enable_chunk_context
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Feat: offload ptable to cpu for chunk context mode
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Fix and add comment
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Update Readme for multimodal and add a new param mm_embedding_offloading
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* fix: Correct prompt table offloading condition in PromptTuningBuffers
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Clean up the code
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Add commits to explain copy from cpu <-> gpu using pinned memory
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Fix namings based on comments
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Fix format based on precommit
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
* Modify --mm_embedding_offloading flag
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
---------
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
* Waive L0 tests
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
* the test is fixed in PR 3711
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
---------
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
* Update Nemotron Super and Ultra in Supported Models and add an example
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
* Update README link to match new examples structure
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
---------
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
This change makes the draft target model works without mismatch in the vocab size
Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>
Co-authored-by: rakib-hasan <rhasan@nvidia.com>
* feat: Integrate GPUDirect Storage (GDS) into Executor API
Squash of several dev commits
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
Signed-off-by: Zheyu Fu <zheyufu2@gmail.com>
Co-authored-by: Junda Chen <32371474+GindaChen@users.noreply.github.com>
Co-authored-by: Yichao Fu <57950249+fuyichao2000@users.noreply.github.com>
Co-authored-by: Andy Dai <zhongdongmin@nvidia.com>
* Add step to generate new duration file
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
* Install python in earlier step
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
* Clone repo and add debug info
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
* Remove debug info and only generate duration for post-merge
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
* Test for the new duration file
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
* Update the duration file format
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
* Move generate_duration.py to scripts folder and add try-catch avoiding any broken
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
---------
Signed-off-by: EmmaQiaoCh <qqiao@nvidia.com>
* feat: adding multimodal (only image for now) support in trtllm-bench
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
* fix: add in load_dataset() calls to maintain the v2.19.2 behavior
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
* re-adding prompt_token_ids and using that for prompt_len
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
* updating the datasets version in examples as well
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
* api changes are not needed
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
* moving datasets requirement and removing a missed api change
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
* addressing review comments
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
* refactoring the quickstart example
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
---------
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
min_latency_mode is only set to False during warmup phase. Thus when it becomes true during inference, all tactics fall back to the default one and thus cause perf regression.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* 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>
