Yang Zheng and Yang Zheng
4dbcbbeb09
[Misc] Compute query_start_loc/seq_start_loc on CPU ( #9447 )
...
Co-authored-by: Yang Zheng(SW)(Alex) <you@example.com >
2024-11-04 08:54:37 +00:00
sroy745
a78dd3303e
[Encoder Decoder] Add flash_attn kernel support for encoder-decoder models ( #9559 )
2024-11-01 23:22:49 -07:00
Peter Salas
6c0b7f548d
[Core][VLM] Add precise multi-modal placeholder tracking ( #8346 )
...
Signed-off-by: Peter Salas <peter@fixie.ai >
2024-11-01 16:21:10 -07:00
sasha0552
55650c83a0
[Bugfix] Fix illegal memory access error with chunked prefill, prefix caching, block manager v2 and xformers enabled together ( #9532 )
...
Signed-off-by: sasha0552 <admin@sasha0552.org >
2024-10-31 11:46:36 -07:00
Thomas Parnell
496e991da8
[Doc] Consistent naming of attention backends ( #9498 )
...
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com >
2024-10-21 22:29:57 +08:00
Kuntai Du
81ede99ca4
[Core] Deprecating block manager v1 and make block manager v2 default ( #8704 )
...
Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).
2024-10-17 11:38:15 -05:00
Lily Liu
89feb4c84d
[SpecDec] Remove Batch Expansion (2/3) ( #9298 )
2024-10-12 05:13:37 +00:00
Lily Liu
1570203864
[Spec Decode] (1/2) Remove batch expansion ( #8839 )
2024-10-01 16:04:42 -07:00
Aaron Pham and Cyrus Leung
9d104b5beb
[CI/Build] Update Ruff version ( #8469 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
2024-09-18 11:00:56 +00:00
sroy745
1009e93c5d
[Encoder decoder] Add cuda graph support during decoding for encoder-decoder models ( #7631 )
2024-09-17 07:35:01 -07:00
Antoni Baum
3b682179dd
[Core] Add AttentionState abstraction ( #7663 )
2024-08-20 18:50:45 +00:00
Antoni Baum
999ef0b917
[Misc] Add numpy implementation of compute_slot_mapping ( #7377 )
2024-08-09 22:52:29 +00:00
Alexander Matveev
e02ac55617
[Performance] Optimize e2e overheads: Reduce python allocations ( #7162 )
2024-08-08 21:34:28 -07:00
Cody Yu
ef527be06c
[MISC] Use non-blocking transfer in prepare_input ( #7172 )
2024-08-05 23:41:27 +00:00
Woosuk Kwon
805a8a75f2
[Misc] Support attention logits soft-capping with flash-attn ( #7022 )
2024-08-01 13:14:37 -07:00
Cody Yu
309aaef825
[Bugfix] Fix decode tokens w. CUDA graph ( #6757 )
2024-07-24 22:33:56 -07:00
Cody Yu
e0c15758b8
[Core] Modulize prepare input and attention metadata builder ( #6596 )
2024-07-23 00:45:24 +00:00
Cyrus Leung
9042d68362
[Misc] Consolidate and optimize logic for building padded tensors ( #6541 )
2024-07-20 04:17:24 +00:00
Cody Yu
2fa4623d9e
[Core] Refactor _prepare_model_input_tensors - take 2 ( #6164 )
2024-07-17 09:37:16 -07:00
afeldman-nm and Woosuk Kwon
543aa48573
[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) ( #4888 )
...
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
2024-07-08 17:12:15 +00:00
