Commit Graph

30 Commits

Author SHA1 Message Date
Lianmin Zheng
693723d1f7 Revert "Tiny refactor DefaultModelLoader.Source" (#5825) 2025-04-28 01:18:57 -07:00
fzyzcjy
644ed409d1 Tiny refactor DefaultModelLoader.Source (#5482) 2025-04-28 00:35:51 -07:00
ryang
bc24205b32 Support BNB quantization for llama/mllama (#5038)
Co-authored-by: Yuhao Yang <yyh073@foxmail.com>
2025-04-15 18:00:31 -07:00
yhyang201
072df75354 Support for Qwen2.5-VL Model in bitsandbytes Format (#5003) 2025-04-14 02:03:40 -07:00
HandH1998
4065248214 Support Llama4 fp8 inference (#5194)
Co-authored-by: laixinn <xielx@shanghaitech.edu.cn>
Co-authored-by: sleepcoo <sleepcoo@gmail.com>
Co-authored-by: zhyncs <me@zhyncs.com>
2025-04-09 20:14:34 +08:00
DangKai
cc88d98ab8 fix empty_cache error in pt_weights_iterator (#5151)
Co-authored-by: dangkai.dk <dangkai.dk@alibaba-inc.com>
2025-04-08 01:22:10 -07:00
inkcherry
7ed77d6b9e fix dummy-load deepseekv2 (#4535) 2025-04-04 15:22:37 -07:00
Brayden Zhong
e84f4ba0ab [Misc] Fix issues reported by torchfix (#4837) 2025-03-27 20:10:32 -07:00
Juwan Yoo
188105a21b deps: lazy import optional dependencies gguf and torchvision (#4826) 2025-03-27 14:35:36 -07:00
huiwq1990
5cbd709ea1 Fix: modelscope env comment (#4474)
Signed-off-by: huiwq1990 <huiwq1990@163.com>
2025-03-16 18:11:33 -07:00
wangyu
1ce4878d31 feat(remote_model): support variable remote backend for model loader (#3964)
Signed-off-by: wangyu <wangyu.steph@bytedance.com>
2025-03-14 00:40:44 -07:00
Lianmin Zheng
45de89719c Revert "[XPU][CPU] Enable the native path of DeepSeek" (#4367) 2025-03-12 23:45:52 -07:00
Meng, Hengyu
71046fcd71 [XPU][CPU] Enable the native path of DeepSeek (#4086)
Co-authored-by: Zhang, Liangang <liangang.zhang@intel.com>
2025-03-12 22:26:29 -07:00
Mick
ff2ce0b86f refactor: move image processors to separate files (#4229) 2025-03-11 12:35:35 -07:00
Lianmin Zheng
aa957102a9 Simplify tests & Fix trtllm custom allreduce registration (#4252) 2025-03-10 01:24:22 -07:00
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
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
Zhiyu
c66b2c9cf1 Add support for nvidia modelopt fp8 kv cache (#3223) 2025-02-22 07:04:58 +08:00
Lianmin Zheng
53cef81587 Improve weight loading and code style (#3174) 2025-01-27 03:00:41 -08:00
Ke Wen
862bcff833 Support loading of larger models with on-the-fly quantization (#3061) 2025-01-22 21:33:17 -08:00
lukec
b8ab989ff4 Fix the FP8 E4M3 parsing offline scales failure bug (#3045) 2025-01-22 14:19:33 -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
Yineng Zhang
5dc54f1a62 feat: remove vllm distributed (#2907)
Co-authored-by: Zhangyi <1109276519@qq.com>
2025-01-17 22:31:51 +08:00
Sangchun Ha (Patrick)
08effbff35 Error occurs when loading the gemma model in bitsandbytes format. (#2557) 2024-12-26 05:10:37 -08:00
Yineng Zhang
85e1a6f3aa Update model_loader deps and qqq quantization deps (#2220) (#2318)
Co-authored-by: HandH1998 <1335248067@qq.com>
2024-12-02 23:22:13 +08:00
Yineng Zhang
9195d1362a misc: rm unused model_loader (#1110) 2024-08-15 08:29:35 -07:00
Ying Sheng
325a06c2de Fix logging (#796) 2024-07-28 23:01:45 -07:00
Yineng Zhang
dd7e8b9421 chore: add copyright for srt (#790) 2024-07-28 23:07:12 +10:00
Ying Sheng
06487f126e refactor model loader: initial refactor (#664) 2024-07-20 02:18:22 -07:00
Ying Sheng
2d96da813e refactor model loader [unreachable code]: initial refactor (#655) 2024-07-19 09:27:06 -07:00