 Ying ShengandKe Bao
|
d3d4d76758
|
[Eagle] Refactor eagle speculative decoding (#3986)
Co-authored-by: Ke Bao <ISPObaoke@163.com>
|
2025-03-05 08:06:07 -08:00 |
|
|
Qubitium-ModelCloudandZX-ModelCloud
|
56a724eba3
|
[QUANT] Add GPTQModel Dynamic Quantization + lm_head Quantization (#3790)
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Co-authored-by: ZX-ModelCloud <zx@modelcloud.ai>
|
2025-03-05 01:11:00 -08:00 |
|
|
Lianmin Zheng
|
e074d84e5b
|
[Minor] more code cleanup (#4077)
|
2025-03-04 21:23:47 -08:00 |
|
|
Lianmin Zheng
|
2dd7d0c533
|
Revert "Fix nightly-test CI" (#4065)
|
2025-03-04 05:38:24 -08:00 |
|
|
Lianmin Zheng
|
935cda944b
|
Misc clean up; Remove the support of jump forward (#4032)
|
2025-03-03 07:02:14 -08:00 |
|
|
|
ac2387279e
|
Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
|
2025-03-03 00:12:04 -08:00 |
|
|
yinfan98
|
b4d34cd35d
|
Fix nightly-test CI (#3826)
|
2025-03-02 23:14:45 -08:00 |
|
|
Lianmin Zheng
|
9e1014cf99
|
Revert "Add fast decode plan for flashinfer mla" (#4008)
|
2025-03-02 19:29:10 -08:00 |
|
|
Baizhou Zhang
|
fa56106731
|
Add fast decode plan for flashinfer mla (#3987)
|
2025-03-02 19:16:37 -08:00 |
|
|
|
90a4b7d98a
|
[Feature]Support ragged prefill in flashinfer mla backend (#3967)
Co-authored-by: Yineng Zhang <me@zhyncs.com>
Co-authored-by: pankajroark <pankajroark@users.noreply.github.com>
|
2025-02-28 18:13:56 -08:00 |
|
|
Chaitanya Sri Krishna Lolla
|
77a6c9d229
|
Remove unused imports from rocm mla kernel. (#3963)
|
2025-02-28 10:01:08 -08:00 |
|
|
Tianxing Wu
|
8b681d7724
|
[Rocm] Fix to the rocm_mla_decode_rope.py returning random result (#3898)
|
2025-02-26 17:05:30 -08:00 |
|
|
Chaitanya Sri Krishna LollaandHAI
|
6ce9dbe828
|
[ROCm] Enable Fused MLA Triton kernel for DeepSeekV3 (#3237)
Co-authored-by: HAI <hixiao@gmail.com>
|
2025-02-24 18:14:31 -08:00 |
|
|
Baizhou Zhang
|
b110084654
|
Refactor flashinfer logic for deepseek v3 and fix accuracy bug (#3785)
|
2025-02-24 04:07:25 -08:00 |
|
|
Ke Bao
|
ddcf9fe3be
|
Optimize triton attention custom mask (#3731)
|
2025-02-21 00:54:41 +08:00 |
|
|
HAI
|
6252ade985
|
revert BLOCK and num_warps on HIP (#3722)
|
2025-02-20 23:30:18 +08:00 |
|
|
Mick
|
99c1b9d2ee
|
fix: apply cache size limit of attention mask for VisionAttention (#3657)
|
2025-02-19 20:16:48 +08:00 |
|
|
|
634a3561ac
|
AMD Prefill optimize (#3665)
Co-authored-by: AMD-dteng <dteng@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
|
2025-02-18 09:35:58 -08:00 |
|
|
Ke Bao
|
e5ce395a6c
|
Fix draft decode max batch size (#3676)
|
2025-02-18 23:03:26 +08:00 |
|
|
Yineng Zhang
|
714f3e6362
|
feat: support flashinfer mla with prefix cache (#3643)
|
2025-02-18 02:06:43 +08:00 |
|
|
Yineng Zhang
|
70f894b810
|
feat: support flashinfer mla attention for deepseek v3 (#3550)
|
2025-02-14 08:50:14 +08:00 |
|
|
Ke Bao
|
7e6d5fc694
|
Support Eagle cuda graph for Triton backend (#3500)
|
2025-02-12 02:27:45 +08:00 |
|
|
Ying Sheng
|
d23cb9a01e
|
[Eagle] reduce one draft forward (#3468)
|
2025-02-10 20:21:49 +08:00 |
|
|
Ke Bao
|
2d61132374
|
Support Eagle2 for Triton backend (#3466)
|
2025-02-10 20:00:42 +08:00 |
|
|
Yineng Zhang
|
27c4c9cf52
|
remove _grouped_size_compiled_for_decode_kernels (#3453)
|
2025-02-10 13:01:21 +08:00 |
|
|
Yineng Zhang
|
36f6fc5093
|
feat: enable ragged fa3 by default on hopper 12.4+ (#3442)
|
2025-02-10 07:43:01 +08:00 |
|
|
Yineng Zhang
|
014cab4dd2
|
update forward_return_lse (#3425)
|
2025-02-09 20:18:44 +08:00 |
|
|
Ying Sheng
|
7b4e61fff3
|
[Fix] Fix eagle with disable cuda graph (#3411)
|
2025-02-09 08:40:00 +08:00 |
|
|
lizamd
|
e868d0b60e
|
update waves_per_eu to 1 (#3356)
|
2025-02-07 13:08:06 +08:00 |
|
|
Ke Bao
|
a322051e31
|
Support custom mask for Triton attention (#3317)
|
2025-02-06 01:16:02 +08:00 |
|
|
Ke Bao
|
de5533341e
|
Update Triton extend backend interface (#3309)
|
2025-02-05 18:12:22 +08:00 |
|
|
Ke Bao
|
a07364ccc5
|
Update Triton decode backend interface (#3292)
|
2025-02-04 23:26:04 +08:00 |
|
|
Yineng Zhangandpankajroark
|
d39899e85c
|
upgrade flashinfer v0.2.0.post2 (#3288)
Co-authored-by: pankajroark <pankajroark@users.noreply.github.com>
|
2025-02-04 21:41:40 +08:00 |
|
|
|
013021b6a1
|
refactor EAGLE 2 (#3269)
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
Co-authored-by: merrymercy <lianminzheng@gmail.com>
Co-authored-by: Ying1123 <sqy1415@gmail.com>
|
2025-02-03 20:52:30 +08:00 |
|
|
Wen-Heng (Jack) Chung
|
d9eb9358cc
|
Tune paged attention parameters for AMD GPU. (#3255)
|
2025-02-01 17:29:45 -08:00 |
|
|
Yineng Zhang
|
7811bfdaa7
|
compatible with flashinfer v0.2 (#3235)
|
2025-02-01 01:32:18 +08:00 |
|
|
Mick
|
9f635ea50d
|
[Fix] Address remaining issues of supporting MiniCPMV (#2977)
|
2025-01-28 00:22:13 -08:00 |
|
|
Lianmin Zheng
|
89cd923581
|
Roll back to use vllm custom allreduce (#3006)
|
2025-01-20 04:03:15 -08:00 |
|
|
|
3d93f84a00
|
[Feature] Support minicpmv v2.6 (#2785)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: yizhang2077 <1109276519@qq.com>
|
2025-01-18 14:14:19 -08:00 |
|
|
Lianmin Zhenganddhou-xai
|
8b6ce52e92
|
Support multi-node DP attention (#2925)
Co-authored-by: dhou-xai <dhou@x.ai>
|
2025-01-16 11:15:00 -08:00 |
|
|
Ke Bao
|
c19d84829c
|
Adjust flashinfer workspace size for Qwen2 models (#2879)
|
2025-01-14 13:34:22 +08:00 |
|
|
bjmsongandroot
|
0bb0f76311
|
Support FP8 E4M3 KV Cache (#2786)
Co-authored-by: root <bjmsong@126.com>
|
2025-01-12 21:17:11 -08:00 |
|
|
Lianmin ZhengandSangBin Cho rkooo567@gmail.com
|
8a6906127a
|
Improve linear.py to load sharded weights & remove the dependency of Parameters from vllm (#2784)
Co-authored-by: SangBin Cho rkooo567@gmail.com
|
2025-01-07 23:29:10 -08:00 |
|
|
|
c7ae474a49
|
[Feature, Hardware] Enable DeepseekV3 on AMD GPUs (#2601)
Co-authored-by: root <root@banff-cyxtera-s83-5.amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: Bruce Xue <yigex@xilinx.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
|
2025-01-02 16:23:19 -08:00 |
|
|
Lianmin Zhengandkavioyu
|
ad20b7957e
|
Eagle speculative decoding part 3: small modifications to the general scheduler (#2709)
Co-authored-by: kavioyu <kavioyu@tencent.com>
|
2025-01-02 02:09:08 -08:00 |
|
|
Lianmin Zhengandyukavio
|
f44d143949
|
Support target model verification in the attention backend (#2678)
Co-authored-by: yukavio <kavioyu@gmail.com>
|
2024-12-30 22:58:55 -08:00 |
|
|
Lianmin Zheng
|
3815b23ccb
|
Clean up wrapper in flashinfer backend (#2638)
|
2024-12-29 00:45:57 -08:00 |
|
|
|
70dc2fbe2d
|
Change extend attention kernel launch parameter for ROCm platform to … (#2610)
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
|
2024-12-27 00:32:17 -08:00 |
|
|
Lianmin Zheng
|
8496701934
|
[Misc] Fix metrics, weight update lock, request logging (#2543)
|
2024-12-22 06:27:22 -08:00 |
|
|
Ke Bao
|
2f9bd0fafd
|
Fix correctness issue for triton decoding kernel (#2479)
|
2024-12-14 16:50:54 +08:00 |
|