Commit Graph

2244 Commits

Author SHA1 Message Date
Yineng Zhang
0aaccbbfec revert deepseek docs (#4109) 2025-03-05 13:23:11 -08:00
Qiaolin Yu
357671e216 Add examples for server token-in-token-out (#4103)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-03-05 13:16:31 -08:00
Chayenne
e70fa279bc Docs: reorganize dpsk docs (#4108) 2025-03-05 13:01:03 -08:00
Tommy Yang
abe74b7b59 Docs: Add DeepSeek optimization ablations documentation (#4107)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-03-05 12:25:51 -08:00
Jhin
70b3c6eeb1 Add update_weights_from_disk endpoint to Engine (#4102)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-03-05 12:25:18 -08:00
Ke Bao
ef9d3b3c2c Fix triton kernel illegal memory issue for eagle (#4100) 2025-03-05 11:23:53 -08:00
Baizhou Zhang
fc91d08a8f [Revision] Add fast decode plan for flashinfer mla (#4012) 2025-03-05 11:20:41 -08:00
HAI
71ab0dabe0 Fix the moe padding conditional logic (#4081) 2025-03-05 10:56:51 -08:00
Ying Sheng
d3d4d76758 [Eagle] Refactor eagle speculative decoding (#3986)
Co-authored-by: Ke Bao <ISPObaoke@163.com>
2025-03-05 08:06:07 -08:00
yigex
5be8f1ed98 ROCM: AITER BLOCK GEMM (#4075) 2025-03-05 03:10:49 -08:00
Lu Changqi
e5760bc40a bench: add dataset param for bench_multiturn (#3990) 2025-03-05 01:21:37 -08:00
Qubitium-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
Mick
583d6af71b example: add vlm to token in & out example (#3941)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-03-04 22:18:26 -08:00
Lianmin Zheng
e074d84e5b [Minor] more code cleanup (#4077) 2025-03-04 21:23:47 -08:00
Qiaolin Yu
4725e3f652 Add examples for returning hidden states when using the server (#4074) 2025-03-04 19:31:50 -08:00
Lianmin Zheng
77a3954bf7 Simplify eagle tests and TP sync in grammar backend (#4066) 2025-03-04 13:40:40 -08:00
Ke Bao
03b0364f76 Update nextn ci test (#4071) 2025-03-04 13:01:24 -08:00
Lianmin Zheng
2dd7d0c533 Revert "Fix nightly-test CI" (#4065) 2025-03-04 05:38:24 -08:00
William
0d4e3228cf [Feature] Add test for speculative_token_map (#4016) 2025-03-04 04:26:24 -08:00
Liu Jinjie
926f8efc0c remove unused max_jobs (#3607)
Signed-off-by: Jinjie Liu <jinjie.liu@usc.edu>
2025-03-04 04:23:39 -08:00
Xiuyu Li
9545bfb28a fix: support gelu_new activation function in gpt2 (#3712) 2025-03-04 04:09:52 -08:00
Michael Feil
37373ef2bb sgl-router - issues on routing and project build. (#3870) (#3948) 2025-03-04 04:06:30 -08:00
Chen Shengzhi
61261b3996 [XCCL] Use xccl for xpu backend since xccl is ready in latest PyTorch. (#3954) 2025-03-04 04:05:56 -08:00
DarkSharpness
19120f71f3 [Fix & Style] Refactor the grammar backend to reduce human errors and improve readability (#4030) 2025-03-04 03:56:45 -08:00
Kebe
2415ec3896 Remove grafana dashboard's datasource uid (#4051) 2025-03-04 03:44:51 -08:00
Qubitium-ModelCloud
87f671ab58 Fix debug_tensor_dump_output_folder optional key missing (#4046) 2025-03-04 03:42:48 -08:00
HAI
51d25405a7 ROCm: update aiter and its usage to fused moe (bloat16, fp8, fp8 block-quant) (#4053) 2025-03-04 03:00:46 -08:00
kk
e0a2c96308 Fix breakage problem when using custom_ar (#4052) 2025-03-04 02:59:03 -08:00
Xihuai Wang
12f2e6c3f1 Fix: #3988 using blockwise_int8 (#4023) 2025-03-03 23:49:58 -08:00
Xihuai Wang
95575aa76a Reasoning parser (#4000)
Co-authored-by: Lucas Pickup <lupickup@microsoft.com>
2025-03-03 21:16:36 -08:00
kk
11eea69e70 Fix assert options.num_stages != 0 error in the latest ROCm build image (#4049)
Co-authored-by: wunhuang <wunhuang@amd.com>
2025-03-03 20:37:03 -08:00
Yineng Zhang
1baa9e6cf9 docs: update README (#4044) 2025-03-03 17:09:18 -08:00
Lianmin Zheng
911fcd0910 Update README.md (#4043) 2025-03-03 16:29:46 -08:00
Ke Bao
9fafa62db7 Share target model embed and head weights for nextn (#4033) 2025-03-03 13:30:04 -08:00
Chayenne
146ac8df07 Add examples in sampling parameters (#4039) 2025-03-03 13:04:32 -08:00
Qiaolin Yu
57a404fd55 Remove outdated test utils and fix links for the doc of sampling params (#3999) 2025-03-03 09:41:38 -08:00
Chayenne
2796fbb53d Docs: Fix sampling parameter (#4034) 2025-03-03 09:32:36 -08:00
Lianmin Zheng
935cda944b Misc clean up; Remove the support of jump forward (#4032) 2025-03-03 07:02:14 -08:00
Lianmin Zheng
110e006673 Reorganize python source files in sgl-kernel with multiple files (#4027) 2025-03-03 06:36:40 -08:00
Lianmin Zheng
6b45a21d16 Reorganize c++ source files in sgl-kernel with multiple folders (#4025) 2025-03-03 05:32:30 -08:00
Yudi Xue
a7000a7650 Update metrics documentation (#3264) 2025-03-03 05:03:58 -08:00
Lianmin Zheng
1a8f995c46 remove cache configs in model definitions (#4031) 2025-03-03 05:00:50 -08:00
Lianmin Zheng
a3ab768a2b Clean up custom allreduce (#4029) 2025-03-03 04:59:53 -08:00
Lianmin Zheng
66301e124f Improve code styles (#4021) 2025-03-03 03:20:23 -08:00
Lianmin Zheng
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
Stefan He
0194948fd9 Optimize Triton Kernel of Group GEMM in DeepGEMM Benchmark (#4014) 2025-03-02 23:29:55 -08:00
yinfan98
b4d34cd35d Fix nightly-test CI (#3826) 2025-03-02 23:14:45 -08:00
Chayenne
728e175fc4 Add examples to token-in-token-out for LLM (#4010) 2025-03-02 21:03:49 -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