Shu Wang
9e96f56efb
Allocate kv_cache with stride order ( #16605 )
...
Signed-off-by: shuw <shuw@nvidia.com >
2025-04-25 22:03:31 -07:00
rasmith and Luka Govedič
a41351f363
[Quantization][FP8] Add support for FP8 models with input_scale for output projection and QK quantization ( #15734 )
...
Signed-off-by: Randall Smith <Randall.Smith@amd.com >
Signed-off-by: Luka Govedič <lgovedic@redhat.com >
Co-authored-by: Luka Govedič <lgovedic@redhat.com >
2025-04-25 00:45:02 -07:00
Mickaël Seznec
a597a57595
[Attention] Flash Attention 3 - fp8 ( #14570 )
...
Signed-off-by: Mickael Seznec <mickael@mistral.ai >
2025-03-20 01:14:20 -04:00
Michael Goin
6832707e90
[V1][Bugfix] Standardize quantized kv cache rejection for attention backends ( #14221 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
2025-03-06 14:18:29 -08:00
Russell Bryant
e489ad7a21
[Misc] Add SPDX-License-Identifier headers to python source files ( #12628 )
...
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com >
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com >
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com >
2025-02-02 11:58:18 -08:00
cabaf4eff3
[Attention] MLA decode optimizations ( #12528 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
Signed-off-by: simon-mo <xmo@berkeley.edu >
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
Co-authored-by: simon-mo <simon.mo@hey.com >
Co-authored-by: Michael Goin <mgoin64@gmail.com >
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com >
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com >
Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com >
Co-authored-by: simon-mo <xmo@berkeley.edu >
2025-01-30 23:49:37 -08:00
Gregory Shtrasberg and Micah Williamson
e97f802b2d
[FP8][Kernel] Dynamic kv cache scaling factors computation ( #11906 )
...
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com >
Co-authored-by: Micah Williamson <micah.williamson@amd.com >
2025-01-23 18:04:03 +00:00
youkaichao
66818e5b63
[core] separate builder init and builder prepare for each batch ( #12253 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2025-01-22 14:13:52 +08:00
wangxiyuan
86bfb6dba7
[Misc] Pass attention to impl backend ( #12218 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
2025-01-20 23:25:28 +08:00
wangxiyuan
2e0e017610
[Platform] Add output for Attention Backend ( #11981 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
2025-01-14 13:27:04 +00:00
Chen Zhang
e20c92bb61
[Kernel] Move attn_type to Attention.__init__() ( #11690 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com >
2025-01-07 00:11:28 +08:00
youkaichao
a4c4daf364
[misc] use out argument for flash attention ( #10822 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2024-12-02 10:50:10 +00:00
youkaichao
eebad39f26
[torch.compile] support all attention backends ( #10558 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2024-11-22 14:04:42 -08:00
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
343f8e0905
Support BERTModel (first encoder-only embedding model) ( #9056 )
...
Signed-off-by: Max de Bayser <maxdebayser@gmail.com >
Signed-off-by: Max de Bayser <mbayser@br.ibm.com >
Co-authored-by: Andrew Feldman <afeldman@neuralmagic.com >
Co-authored-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com >
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
Co-authored-by: laishzh <laishengzhang@gmail.com >
Co-authored-by: Max de Bayser <maxdebayser@gmail.com >
Co-authored-by: Max de Bayser <mbayser@br.ibm.com >
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
2024-10-17 23:21:01 +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
William Lin
a6c0f3658d
[multi-step] add flashinfer backend ( #7928 )
2024-09-12 11:16:22 -07:00
Antoni Baum
3b682179dd
[Core] Add AttentionState abstraction ( #7663 )
2024-08-20 18:50:45 +00:00
William Lin and Cody Yu
f366f6339b
[spec decode] [4/N] Move update_flash_attn_metadata to attn backend ( #7571 )
...
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com >
2024-08-16 11:41:56 -07:00
Woosuk Kwon
805a8a75f2
[Misc] Support attention logits soft-capping with flash-attn ( #7022 )
2024-08-01 13:14:37 -07:00
Cody Yu
e0c15758b8
[Core] Modulize prepare input and attention metadata builder ( #6596 )
2024-07-23 00:45:24 +00:00
Cody Yu
2fa4623d9e
[Core] Refactor _prepare_model_input_tensors - take 2 ( #6164 )
2024-07-17 09:37:16 -07:00
Michael Goin
978aed5300
[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale ( #6081 )
2024-07-16 15:31:32 -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
Stephanie Wang and Stephanie
dda4811591
[Core] Refactor Worker and ModelRunner to consolidate control plane communication ( #5408 )
...
Signed-off-by: Stephanie Wang <swang@cs.berkeley.edu >
Signed-off-by: Stephanie <swang@anyscale.com >
Co-authored-by: Stephanie <swang@anyscale.com >
2024-06-25 20:30:03 -07:00
8e192ff967
[Kernel][Backend][Model] Blocksparse flash attention kernel and Phi-3-Small model ( #4799 )
...
Co-authored-by: beagleski <yunanzhang@microsoft.com >
Co-authored-by: bapatra <bapatra@microsoft.com >
Co-authored-by: Barun Patra <codedecde@users.noreply.github.com >
Co-authored-by: Michael Goin <michael@neuralmagic.com >
2024-05-24 22:00:52 -07:00
SangBin Cho
65bf2ac165
[Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API ( #4681 )
...
This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.
It also refactors subquery_start_loc which was not refactored in the previous PR
2024-05-15 14:00:10 +09:00
Woosuk Kwon
0fca3cdcf2
[Misc] Enhance attention selector ( #4751 )
2024-05-13 10:47:25 -07:00
youkaichao
20cfcdec99
[Core][Optimization] change python dict to pytorch tensor for blocks to swap ( #4659 )
2024-05-08 12:07:05 -07:00
Woosuk Kwon
5510cf0e8a
[Misc] Add get_name method to attention backends ( #4685 )
2024-05-08 09:59:31 -07:00
youkaichao
63575bc2e1
[Core][Optimization] change python dict to pytorch tensor ( #4607 )
2024-05-06 21:30:27 -07:00
Lily Liu and LiuXiaoxuanPKU
43c413ec57
[Kernel] Use flashinfer for decoding ( #4353 )
...
Co-authored-by: LiuXiaoxuanPKU <llilyliupku@gmail.com >
2024-05-03 15:51:27 -07:00
SangBin Cho
0ae11f78ab
[Mypy] Part 3 fix typing for nested directories for most of directory ( #4161 )
2024-04-22 21:32:44 -07:00
SangBin Cho
67b4221a61
[Core][5/N] Fully working chunked prefill e2e ( #3884 )
2024-04-10 17:56:48 -07:00
+2
2ff767b513
Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) ( #3290 )
...
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com >
Co-authored-by: HaiShaw <hixiao@gmail.com >
Co-authored-by: AdrianAbeyta <Adrian.Abeyta@amd.com >
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com >
Co-authored-by: root <root@gt-pla-u18-08.pla.dcgpu >
Co-authored-by: mawong-amd <156021403+mawong-amd@users.noreply.github.com >
Co-authored-by: ttbachyinsda <ttbachyinsda@outlook.com >
Co-authored-by: guofangze <guofangze@kuaishou.com >
Co-authored-by: Michael Goin <mgoin64@gmail.com >
Co-authored-by: jacobthebanana <50071502+jacobthebanana@users.noreply.github.com >
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
2024-04-03 14:15:55 -07:00
Woosuk Kwon
925f3332ca
[Core] Refactor Attention Take 2 ( #3462 )
2024-03-25 04:39:33 +00:00
Shu Wang