Commit Graph

127 Commits

Author SHA1 Message Date
yiakwy-xpu-ml-framework-team
10bfce71b3 fix moe align blocks benchmark (#3003) 2025-01-20 19:33:29 +08:00
Xiaoyu Zhang
83452dbb4a fix file name spelling mistake and useless variable in minmax-text-01-lightning_attention (#2971) 2025-01-18 18:56:13 -08:00
Xiaoyu Zhang
c2f212d672 optimize MiniMax-Text-01 lightning_attn_decode triton (#2966) 2025-01-18 23:41:01 +08:00
Zhiqiang Xie
13387e6b7a Multi-turn benchmark for hierarchical caching (#2942) 2025-01-17 16:17:24 -08:00
Xiaoyu Zhang
78e974b2a5 [kernel] MiniMax-Text-01 decode lightning_attn with triton (#2920) 2025-01-16 12:51:38 -08:00
Lianmin Zheng
bc6915e3b9 Improve type annotation and styles (#2926) 2025-01-16 12:51:11 -08:00
Xiaoyu Zhang
ab31793661 [kernel] MiniMax-Text-01 prefill lightning_attn with triton (#2911) 2025-01-16 14:18:29 +08:00
Yineng Zhang
80002562a8 docs: update README (#2878) 2025-01-14 12:48:17 +08:00
Lianmin Zheng
46d4431889 Add a new api configure_logging to allow dumping the requests (#2875) 2025-01-13 14:24:00 -08:00
Xiaoyu Zhang
d08c77c434 Sampling penalties memory interface (#2870) 2025-01-13 23:09:00 +08:00
Yineng Zhang
41d7e5b7e6 docs: update link (#2857) 2025-01-13 18:40:48 +08:00
Lianmin Zheng
72c7776355 Fix linear.py and improve weight loading (#2851)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
2025-01-13 01:39:14 -08:00
Ke Bao
85b2e05770 Add int8 quant kernel (#2848) 2025-01-13 13:16:58 +08:00
Yineng Zhang
197cbf9bab docs: update README (#2841) 2025-01-11 23:11:38 +08:00
Yineng Zhang
f624901cdd chore: bump v0.4.1.post5 (#2840) 2025-01-11 23:10:02 +08:00
sleepcoo
4f077c01b8 minor: support specifying local dataset path for gsm8k and hellaswag (#2816) 2025-01-09 22:24:42 +08:00
Lianmin Zheng
bdc1acf6cd Misc fix for min_p_sampling, --cuda-graph-bs (#2761) 2025-01-07 02:52:53 -08:00
Xiaoyu Zhang
380930a959 add benchmark_moe_align_blocks (#2767) 2025-01-07 14:20:50 +08:00
Rodrigo Garcia
a990daff9c Included multi-node DeepSeekv3 example (#2707) 2025-01-02 22:17:03 +08:00
Lianmin Zheng
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 Zheng
8c3b420eec [Docs] clean up structured outputs docs (#2654) 2024-12-29 23:57:16 -08:00
Yineng Zhang
098d659c0e docs: update README (#2651) 2024-12-30 13:33:29 +08:00
Lzhang-hub
76d14f8cb9 add 2*h20 node serving example for deepseek v3 (#2650)
Co-authored-by: Yineng Zhang <me@zhyncs.com>
2024-12-30 13:04:38 +08:00
Lianmin Zheng
03d5fbfd44 Release 0.4.1.post3 - upload the config.json to PyPI (#2647) 2024-12-29 14:25:53 -08:00
Yineng Zhang
763dd55d17 docs: update README (#2644) 2024-12-30 01:24:06 +08:00
HandH1998
afa0341e57 Update Triton configs for block fp8 kernels (#2641) 2024-12-29 22:53:47 +08:00
Yineng Zhang
7863e4368a add configs for block fp8 related kernels (#2628)
Co-authored-by: HandH1998 <1335248067@qq.com>
2024-12-28 23:12:04 +08:00
Ke Bao
8a2681e26a Update readme (#2625) 2024-12-28 13:39:56 +08:00
Yineng Zhang
d9e6ee382b docs: update README (#2618) 2024-12-28 00:21:53 +08:00
Lianmin Zheng
f46f394f4d Update README.md (#2605) 2024-12-26 10:58:49 -08:00
Lianmin Zheng
773951548d Fix logprob_start_len for multi modal models (#2597)
Co-authored-by: libra <lihu723@gmail.com>
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
Co-authored-by: Wang, Haoyu <haoyu.wang@intel.com>
2024-12-26 06:27:45 -08:00
fsygd
637de9e8ce update readme of DeepSeek V3 (#2596) 2024-12-26 21:31:56 +08:00
Xiaoyu Zhang
9a23c48456 h100 tuning fused_moe_triton for qwen2 moe (#2560) 2024-12-26 03:13:31 -08:00
Yineng Zhang
635a042623 docs: update deepseek v3 example (#2592) 2024-12-26 17:43:37 +08:00
Yineng Zhang
75ad0a143f docs: add deepseek v3 launch instructions (#2589) 2024-12-25 23:26:54 -08:00
Ke Bao
e835a50021 Reorg moe code (#2563) 2024-12-24 01:10:22 +08:00
Xiaoyu Zhang
7d672d277b [kernel optimize] benchmark write_req_to_token_pool_triton and optimize kernel (#2509) 2024-12-22 02:31:02 -08:00
bjmsong
e21026690d benchmark decoding attention kernel with cudnn (#2467)
Co-authored-by: root <bjmsong@126.com>
2024-12-17 03:31:57 -08:00
Lianmin Zheng
56198b45d9 Add a benchmark script for in-batch prefix caching (#2494) 2024-12-16 18:49:02 -08:00
Xiaoyu Zhang
a0592c059f [Benchmark] add a benchmark for hf/vllm/sglang rmsnorm (#2486) 2024-12-15 13:52:08 +08:00
bjmsong
f67723940d decoding attention kernel benchmark (#2425)
Co-authored-by: root <bjmsong@126.com>
2024-12-11 04:46:59 -08:00
Xiaoyu Zhang
3844feb9bb Add a unittest for fused_moe (#2416) 2024-12-08 22:46:10 -08:00
Lianmin Zheng
07ec07ad1f Improve torch compile for fused moe (#2327) 2024-12-03 01:58:25 -08:00
Lianmin Zheng
33deca81b5 Add more fused moe benchmark utilities (#2314) 2024-12-02 04:26:55 -08:00
Xiaoyu Zhang
262e370f78 [benchmark] Add fused_moe_triton benchmark and tuning tools (#2225)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: HAI <hixiao@gmail.com>
2024-11-29 13:36:45 -08:00
Henry Hyeonmok Ko
dbe1729395 Merged three native APIs into one: get_server_info (#2152) 2024-11-24 01:37:58 -08:00
Byron Hsu
cbedd1db1d [router] cache-aware load-balancing router v1 (#2114) 2024-11-23 08:34:48 -08:00
Xuehai Pan
62a4a339eb docs: fix module docstrings and copyright headers (#2077) 2024-11-22 22:16:53 +08:00
Lianmin Zheng
c29b98e043 Fix json benchmark (#2043) 2024-11-15 05:33:43 -08:00
DarkSharpness
954f4e6bd6 benchmark json schema (#2030) 2024-11-15 05:06:19 -08:00