Commit Graph

84 Commits

Author SHA1 Message Date
Mick
9f635ea50d [Fix] Address remaining issues of supporting MiniCPMV (#2977) 2025-01-28 00:22:13 -08:00
Byron Hsu
27aeb4b7d8 [test] deduplicate test_session_control (#3183) 2025-01-28 13:17:06 +08:00
yizhang2077
1e3e521544 add unit test for block wise fp8 (#3156) 2025-01-27 15:32:04 +08:00
Lianmin Zheng
d1a0863251 Add a test case for cached_tokens (#3145) 2025-01-26 01:39:28 -08:00
Lianmin Zheng
cd493b5afc Improve metrics, logging, and importing orders (#2992) 2025-01-19 18:36:59 -08:00
Enrique Shockwave
3bcf5ecea7 support regex in xgrammar backend (#2983) 2025-01-20 04:34:41 +08:00
bjmsong
d3024f4fc8 support e4m3 kvcache in qwen2 & add kv scaling facotr json (#2894)
Co-authored-by: bjmsong <bjmsong@126.com>
2025-01-18 11:43:22 +08:00
Ke Bao
d47c5101f1 Add ut for qwen model (#2947) 2025-01-18 00:03:54 +08:00
Chang Su
a8ccacc8b8 [Frontend] Fix request length check and add option to disallow auto truncation in scheduler (#2876) 2025-01-16 14:51:19 -08:00
yizhang2077
767c9dec03 adapt custom allreduce for tensorrt llm (#2511) 2025-01-16 04:57:35 +08:00
Ke Bao
bfbda62c8b Add ut for w8a8 int8 quantization (#2897) 2025-01-15 18:29:14 +08:00
fzyzcjy
923f518337 CUDA-graph-compatible releasing and resuming KV cache and model weight memory (#2630) 2025-01-13 11:38:51 -08:00
Lianmin Zheng
67008f4b32 Use only one GPU for MLA CI tests (#2858) 2025-01-13 03:55:33 -08:00
Shi Shuai
c4f9707e16 Improve: Token-In Token-Out Usage for RLHF (#2843) 2025-01-11 15:14:26 -08:00
Lianmin Zheng
b22f3f6475 Fix nightly accuracy tests (#2780) 2025-01-07 21:02:35 -08:00
Lianmin Zheng
6fb5768372 Disable math eval on nightly CI temporarily (#2779) 2025-01-07 18:17:34 -08:00
yukavio
815dce0554 Eagle speculative decoding part 4: Add EAGLE2 worker (#2150)
Co-authored-by: kavioyu <kavioyu@tencent.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2025-01-02 03:22:34 -08:00
Xiaotong Jiang
a4d6d6f1dd [feat]: Add math eval to CI nightly run (#2663)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
2025-01-01 15:29:35 -08:00
Shi Shuai
35bdb48557 [Feature] Get Token IDs with Engine.generate() (#2636)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
2024-12-29 12:28:27 -08:00
fzyzcjy
fd28640dc5 Add update_weights_from_tensor (#2631) 2024-12-28 13:30:27 -08:00
Lianmin Zheng
855d0ba381 [CI] Fix nightly test and raise better error message (#2626)
Co-authored-by: Sangbin <rkooo567@gmail.com>
2024-12-27 22:16:39 -08:00
Lianmin Zheng
dc3bee4815 Fix test and benchmark scripts (#2598) 2024-12-26 07:56:26 -08:00
Lianmin Zheng
9cd9dc83b3 Temporarily disable unit test of torch native attention backend (#2492) 2024-12-16 14:17:27 -08:00
Ying Sheng
8586b72da0 [feat] Enable chunked prefill for llava-onevision (#2412) 2024-12-09 09:52:38 -08:00
Lianmin Zheng
641b7d0ae0 [Minor] Improve code style (#2422) 2024-12-09 06:30:35 -08:00
Xiaoyu Zhang
3844feb9bb Add a unittest for fused_moe (#2416) 2024-12-08 22:46:10 -08:00
Ying Sheng
aa47f64223 Revert "[feat] Enable chunked prefill for llava-onevision" (#2329) 2024-12-02 23:11:13 -08:00
Ying Sheng
480e38a733 [feat] Enable chunked prefill for llava-onevision (#2281) 2024-12-02 20:19:02 -08:00
Qun Yang
62c516ac45 Add a simple torch native attention backend (#2241) 2024-12-01 03:01:25 -08:00
Lianmin Zheng
9449a95431 [CI] Balance CI tests (#2293) 2024-12-01 01:47:30 -08:00
Lianmin Zheng
0303ca918f [CI] Fix missing files in run_suite.py (#2288) 2024-11-30 23:53:34 -08:00
Lianmin Zheng
4936be8acc Revert "Revert "[FEAT] Support GGUF format"" (#2287) 2024-11-30 22:14:48 -08:00
Lianmin Zheng
7e4c6dd8da Revert "[FEAT] Support GGUF format" (#2285) 2024-11-30 19:03:26 -08:00
Yang Zheng
883c955489 [FEAT] Support GGUF format (#2215)
Co-authored-by: Yang Zheng(SW)(Alex) <you@example.com>
2024-11-30 00:44:48 -08:00
Chayenne
7d1485d376 Add get weights by parameter name for llama (#2266) 2024-11-29 23:36:38 -08:00
Lianmin Zheng
b2ccf36d4d Fix memory leak during abort (#2238) 2024-11-28 02:22:15 -08:00
Ying Sheng
37c8a5761f [feat] Support session control for vision language models (#2210) 2024-11-27 00:03:29 -08:00
Lianmin Zheng
1605ae121e [CI] Minor fix for CI (#2187) 2024-11-25 16:38:43 -08:00
Rin Intachuen
1aea19f64b Input_embeds support (#2052) 2024-11-25 16:35:04 -08:00
Ying Sheng
e1e595d702 [feat] Refactor session control interface and add CI (#2173) 2024-11-25 12:32:51 -08:00
Lianmin Zheng
254fd130e2 [CI] Split test cases in CI for better load balancing (#2180) 2024-11-25 04:58:16 -08:00
Lianmin Zheng
7d671e4ad2 Enable overlap by default (#2067) 2024-11-19 22:07:58 -08:00
Lianmin Zheng
c3eac1b010 Fix torch.compile for MoE (#2033) 2024-11-14 01:30:24 -08:00
Lianmin Zheng
9c939a3d8b Clean up metrics code (#1972) 2024-11-09 15:43:20 -08:00
Lianmin Zheng
2ce32db6fb Let reward model take text inputs instead of message lists (#1907)
Co-authored-by: Kyle Corbitt <kyle@corbt.com>
2024-11-03 13:27:12 -08:00
Lianmin Zheng
c17c578108 Simplify tokenizer manager (#1904) 2024-11-03 08:38:26 -08:00
Lianmin Zheng
a2e0424abf Fix memory leak for chunked prefill 2 (#1858)
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
2024-10-31 14:51:51 -07:00
Ke Bao
c77762d57f Fix Triton decode kernel & ut (#1819) 2024-10-27 10:54:38 -07:00
Lianmin Zheng
e646c5901e Fix logprob in the overlapped mode (#1795) 2024-10-25 11:06:57 -07:00
Lianmin Zheng
40900baea7 [Fix] Fix the log parsing in chunked prefill uni tests (#1794) 2024-10-25 08:31:08 -07:00