hf_text-generation-inference/benchmark/src
OlivierDehaene a6a0c97ed9
feat: prefill chunking (#2600)
* wip

* rollback

* refactor to use prefix/postfix namming + fix all_input_ids_tensor

* maybe patching vlms?

* fix filter and concat

* wip, no filter, no concat

* current

* add prepare_for_prefill

* working

* load tested

* re-create slots

* re-create slots

* fix slot_filtering_indices

* feedback loop

* remove log

* fix benchmarker

* fix vlm and seq2seq

* rename to cache and input lengths

* fix prefill logprobs

* fix launcher

* fix logprobs?

* idk at this point

* max input length

* omfg

* remove debugging lines

* fix tests

* fix mllama

* fix cargo tests

* remove support chunking for paged

* Fixing non blocked attentions

* Fixing dtype + AMD, Ipex targets.

* lint fix.

* rename

* Fix prefix_caching variable, remove defaults in server (confusing a lot
of the times).

* Add simple resolution when user specifies ATTENTION=paged.

* Put back non default simple tests.

* Fix env name

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-10-16 12:49:33 +02:00
..
app.rs Simplify crossterm imports (#2545) 2024-09-24 14:57:20 +02:00
event.rs Simplify crossterm imports (#2545) 2024-09-24 14:57:20 +02:00
generation.rs feat: prefill chunking (#2600) 2024-10-16 12:49:33 +02:00
lib.rs Hotfixing main. (#2562) 2024-09-24 23:00:43 +02:00
main.rs feat: prefill chunking (#2600) 2024-10-16 12:49:33 +02:00
table.rs Set maximum grpc message receive size to 2GiB (#2075) 2024-06-17 16:40:44 +02:00
utils.rs Set maximum grpc message receive size to 2GiB (#2075) 2024-06-17 16:40:44 +02:00