|
|
ac201a0eaf
|
[Feature] Support Decode Context Parallel (DCP) for MLA (#23734)
Signed-off-by: hongchao <hongchao@msh.team>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: hongchao <hongchao@msh.team>
Co-authored-by: youkaichao <youkaichao@gmail.com>
|
2025-09-06 13:24:05 +08:00 |
|
|
|
006477e60b
|
[ROCm][Fix] Fix rocm build caused by #23791 (#23847)
Signed-off-by: charlifu <charlifu@amd.com>
|
2025-08-28 19:52:27 -07:00 |
|
|
|
186aced5ff
|
[Kernel] cuda kernels for upcoming decode context parallel feature (#23791)
Co-authored-by: hongchao <hongchao@msh.team>
|
2025-08-28 15:29:11 +08:00 |
|
|
|
19fe1a0510
|
[Kernel] Add FP8 support with FlashMLA backend (#22668)
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
|
2025-08-22 02:26:32 +00:00 |
|
|
|
eefbf4a68b
|
[Perf] Optimize reshape_and_cache_flash CUDA Kernel (#22036)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-01 19:18:51 -04:00 |
|
|
|
9e96f56efb
|
Allocate kv_cache with stride order (#16605)
Signed-off-by: shuw <shuw@nvidia.com>
|
2025-04-25 22:03:31 -07:00 |
|
|
|
64fc2193dc
|
[Misc][Docs] fix the comments of KV_T and CACHE_T in CALL_RESHAPE_AND_CACHE_XX macros (#14347)
|
2025-03-18 05:50:19 -07:00 |
|
|
|
378b3ef6f8
|
[ROCm][V1] Update reshape_and_cache to properly work with CUDA graph padding (#13922)
|
2025-02-26 20:04:12 -08:00 |
|
|
|
288cc6c234
|
[Attention] MLA with chunked prefill (#12639)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Patrick Horn <patrick.horn@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2025-02-21 15:30:12 -08:00 |
|
|
|
75e94309e8
|
[Perf] Mem align KV caches for CUDA devices (MLA perf improvement) (#12676)
Signed-off-by: simon-mo <xmo@berkeley.edu>
Signed-off-by: Lucas Wilkinson <lcwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
|
2025-02-04 18:22:24 -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 |
|
|
|
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 |
|
|
|
3b61cb450d
|
[V1] Further reduce CPU overheads in flash-attn (#10989)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-09 12:38:46 -08:00 |
|
|
|
0e63494cf3
|
Add fp8 support to reshape_and_cache_flash (#6667)
|
2024-07-24 18:36:52 +00:00 |
|
|
|
978aed5300
|
[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)
|
2024-07-16 15:31:32 -07:00 |
|
|
|
5467ac3196
|
[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047)
|
2024-06-09 16:23:30 -04:00 |
|
|
|
5f6d10c14c
|
[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)
|
2024-05-22 07:18:41 +00:00 |
|
|
|
c833101740
|
[Kernel] Refactor FP8 kv-cache with NVIDIA float8_e4m3 support (#4535)
|
2024-05-09 18:04:17 -06:00 |
|
|
|
20cfcdec99
|
[Core][Optimization] change python dict to pytorch tensor for blocks to swap (#4659)
|
2024-05-08 12:07:05 -07:00 |
|
|
|
63575bc2e1
|
[Core][Optimization] change python dict to pytorch tensor (#4607)
|
2024-05-06 21:30:27 -07:00 |
|
|
|
43c413ec57
|
[Kernel] Use flashinfer for decoding (#4353)
Co-authored-by: LiuXiaoxuanPKU <llilyliupku@gmail.com>
|
2024-05-03 15:51:27 -07:00 |
|
|
|
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 |
|
|
|
d6e4a130b0
|
[Minor] Remove gather_cached_kv kernel (#3043)
|
2024-02-26 15:00:54 -08:00 |
|
|
|
923797fea4
|
Fix compile error when using rocm (#2648)
|
2024-02-01 09:35:09 -08:00 |
|
|
|
9090bf02e7
|
Support FP8-E5M2 KV Cache (#2279)
Co-authored-by: zhaoyang <zhao.yang16@zte.com.cn>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
|
2024-01-28 16:43:54 -08:00 |
|
|
|
5265631d15
|
use a correct device when creating OptionalCUDAGuard (#2583)
|
2024-01-25 23:48:17 -08:00 |
|
|
|
77af974b40
|
[FIX] Support non-zero CUDA devices in custom kernels (#1959)
|
2024-01-02 19:09:59 -08:00 |
|
|
|
6ccc0bfffb
|
Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)
Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
Co-authored-by: Amir Balwel <amoooori04@gmail.com>
Co-authored-by: root <kuanfu.liu@akirakan.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: kuanfu <kuanfu.liu@embeddedllm.com>
Co-authored-by: miloice <17350011+kliuae@users.noreply.github.com>
|
2023-12-07 23:16:52 -08:00 |
|
|
|
0ce8647dc5
|
Fix integer overflows in attention & cache ops (#1514)
|
2023-10-31 15:19:30 -07:00 |
|
|
|
c1376e0f82
|
Change scheduler & input tensor shape (#1381)
|
2023-10-16 17:48:42 -07:00 |
|
|
|
8ce9c50d40
|
Avoid compiling kernels for double data type (#933)
|
2023-09-02 14:59:47 +09:00 |
|
|
|
0b98ba15c7
|
Change the name to vLLM (#150)
|
2023-06-17 03:07:40 -07:00 |
|
|
|
e070829ae8
|
Support bfloat16 data type (#54)
|
2023-05-03 14:09:44 -07:00 |
|
|
|
e3cec88aa5
|
Memcpy kernel for flash attention (#29)
* optimize
* add benchmark
* add assert
* add test
|
2023-04-10 18:22:49 -07:00 |
|
|
|
0f40557af6
|
Implement block copy kernel to optimize beam search (#32)
|
2023-04-07 17:45:07 -07:00 |
|
|
|
897cb2ae28
|
Optimize data movement (#20)
|
2023-04-02 00:30:17 -07:00 |
|
|
|
88c0268a18
|
Implement custom kernel for LLaMA rotary embedding (#14)
|
2023-03-30 11:04:21 -07:00 |
|
|
|
cfae35b861
|
Add miscellaneous updates (#8)
|
2023-03-13 13:48:38 -07:00 |
|
|
|
1a7eb7da61
|
Support beam search & parallel generation (#7)
|
2023-03-10 09:58:21 -08:00 |
|
|
|
0deacbce6e
|
Implement single_query_cached_kv_attention kernel (#3)
|
2023-03-01 15:02:19 -08:00 |
|
|
|
c413c41cda
|
Add reshape_and_cache op
|
2023-02-18 19:22:57 +00:00 |
|
|
|
ffad4e1e03
|
cache_kernel -> cache_kernels
|
2023-02-16 20:05:45 +00:00 |
|
