4090 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
周周周	e9174f25e8	commit (#5452)	2025-12-09 19:36:58 +08:00
chen	b491dcd23c	[Optimization] compulte real max_logprobs in batch (#5430) (#5448)	2025-12-09 16:48:06 +08:00
gaoziyuan	2c55bbc3f8	support dynamic load for normal (#5437)	2025-12-09 15:07:19 +08:00
周周周	4b9e2c5c8e	[BugFix] 0 not into cuda graph to save memory (#5426) (#5432)	2025-12-09 11:08:55 +08:00
Yonghua Li	31436a35e4	[Cherry-Pick] [BugFix] [RL] remove shutdown_process_group/restart_process_group for RL (#5433) (#5434) ... * [fix] remove shutdown_process_group/restart_process_group for RL * [chore] remove log * [chore] remove log * [chore] set log to debug level	2025-12-08 19:13:06 +08:00
周周周	d4c16aa63e	[BugFix][Cherry-Pick] fix can not enter into cuda graph (#5423) ... * fix bug * fix bug	2025-12-08 13:12:27 +08:00
Jiang-Jia-Jun	1dceb1c48c	Update setup.py	2025-12-08 11:21:26 +08:00
Nyakku Shigure	7926add37c	[Cherry-Pick][Loader][BugFix] Fix some parameters place on CPU in PaddleOCR-VL (#5413) (#5414) ... * [BugFix] Fix some parameter place on CPU in PaddleOCR-VL * clean log * fix codestyle	2025-12-08 10:01:20 +08:00
RAM	707d1a1fc9	[New][RL] Support Rollout Routing Replay (#5405) (#5408) ... * [RL] Support Rollout Routing Replay * add routing indices cache * fix config bug and moe forward bug * R3 Support GLM * support eb4.5 * fix merge bug * Apply suggestion from @Copilot * Apply suggestion from @Copilot * Apply suggestion from @Copilot * Apply suggestion from @Copilot * add routing replay ci * support glm topk * support orther top_k * fix ci bug * pre-commit * only support chatcmpl * Revert "Revert "[RL] Support Rollout Routing Replay (#5321)" (#5402)" This reverts commit c45e064f3d. * Fix XPU and NPU bug --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>	2025-12-08 10:00:35 +08:00
bukejiyu	7eea23f238	cp pr5373 pr5379 pr5410 (#5411)	2025-12-06 00:47:01 +08:00
Jiang-Jia-Jun	c45e064f3d	Revert "[RL] Support Rollout Routing Replay (#5321)" (#5402) ... This reverts commit 96d2d4877b.	2025-12-05 20:19:39 +08:00
周周周	94c57e4175	[BugFix]remove _execute_empty_input (#5396)	2025-12-05 20:19:01 +08:00
lizexu123	d4979347ca	[Bug fix] Fix the multi-input accuracy issue in the pooling model. (#5374) ... * fix multi-inputs * fix threshold * fix threshold * fix	2025-12-05 20:18:17 +08:00
RAM	96d2d4877b	[RL] Support Rollout Routing Replay (#5321) ... * [RL] Support Rollout Routing Replay * add routing indices cache * fix config bug and moe forward bug * R3 Support GLM * support eb4.5 * fix merge bug * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * add routing replay ci * support glm topk * support orther top_k * fix ci bug * pre-commit * only support chatcmpl --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>	2025-12-05 20:01:33 +08:00
GoldPancake	8545b705ed	fix top_p_candidates (#5400) ... Co-authored-by: freeliuzc <lzc842650834@gmail.com>	2025-12-05 20:01:05 +08:00
wyw	bae3475926	[BugFix]Fix plugin loading logic and logging messages (#4909) ... * Fix plugin loading logic and logging messages * Fix indentation in plugin loading logic --------- Co-authored-by: gaoziyuan <88373061+gzy19990617@users.noreply.github.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>	2025-12-05 19:25:01 +08:00
kevin	db936ab3e4	fix mtp prefix_cache dy-c8 bug (#5390)	2025-12-05 19:03:19 +08:00
kevin	c9d7f9e7c3	[BugFix] fix async download bug (#5349) ... * fix async download bug * update log * Revert "update log" This reverts commit 5816e602f4. * update code * fix mtp bug	2025-12-05 18:59:12 +08:00
zccjjj	5b900667e3	[XPU] support ep4tp1+v1 loader (#5398)	2025-12-05 18:51:15 +08:00
Yonghua Li	35846909c7	[fix] fix scheduler hang when input length is very close to max_model_len (#5393)	2025-12-05 18:23:42 +08:00
Ayakouji	a8f8791668	[Optimization] Qwen2.5-VL support multi-batch prefill (#5269) ... * update * fix Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix dict access --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-12-05 18:22:39 +08:00
Lucas	8f2b85362d	[XPU] support moe_expert_ffn TGEMM selection (#5375)	2025-12-05 17:49:40 +08:00
Lucas	3aed8d257d	[XPU] redirect xvllm/xtdk/xhpc downloading log (#5388)	2025-12-05 17:34:17 +08:00
周周周	c83dc58105	[Feature] support Two batch overlap, mainly used in Prefill (#5078)	2025-12-05 14:58:50 +08:00
qwes5s5	1aefbef0b3	fix trace log (#5386)	2025-12-05 14:45:52 +08:00
lizhenyun01	d436640735	[BugFix] Fix flash_attn_backend	2025-12-05 14:33:38 +08:00
cmcamdy	86b6430582	fix split_rope_cache_kv_encoder in mix mtp (#5384)	2025-12-05 14:33:17 +08:00
Jiaxin Sui	b5a7abe624	[XPU] [CI] Change Paddle Version to Nightly (#5346) ... * Enhance run_ci_xpu.sh with caching and prefill options * Update model path and configuration in run_ci_xpu.sh * Add '北朝' keyword to assertion in run_45vl.py * Enhance process termination logic in run_ci_xpu.sh * Set timeout for CI_XPU job to 60 minutes * Remove extra newline in stop_processes function * Update paddlepaddle-xpu installation command Comment out the previous paddlepaddle-xpu installation command and replace it with a specific version installation due to EP parallel error. * Update PaddlePaddle installation command	2025-12-05 13:01:29 +08:00
fmiao2372	ebe613ccc8	[Intel HPU] fix bug about RP 5138 (#5380)	2025-12-05 11:33:29 +08:00
Lucas	7b0b6e470a	[XPU] support XDNN downloading function (#5365)	2025-12-05 11:16:45 +08:00
ming1753	dd2e9a14c7	[BugFix] Compatible with asynchronous functions (#5378) ... * [BugFix] fix data_processor asyn bug * fix bug	2025-12-05 11:05:21 +08:00
zccjjj	e927c65742	[XPU] [Optimization] [EP] EP communication optimization. (#5145)	2025-12-05 10:03:45 +08:00
bukejiyu	620d1da1c9	deepseek torch (#5373)	2025-12-04 23:26:53 +08:00
YuBaoku	1b5fd79d6b	[CI] disable test_schedule_output.py in unit_test (#5377)	2025-12-04 23:18:23 +08:00
Juncai	7f4fff4d1e	fix get_request from scheduler (#5369)	2025-12-04 21:59:10 +08:00
chenjian	3878a99b69	[Fearture] Support cache kv cache for output tokens (#4535) ... * [Fearture] Support cache kv cache for output tokens * fix bug * fix ci bug * improve coverage * enable output caching by default * fix ci --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-12-04 20:53:08 +08:00
Yonghua Li	b6f8069b36	[fix] update check_model_weights_status loop (#5249)	2025-12-04 19:43:01 +08:00
Yuanle Liu	41c63f6056	remove fastsafetensors (#5371)	2025-12-04 19:22:04 +08:00
xiegegege	b7e1e6c953	[CE]change yaml name	2025-12-04 19:14:11 +08:00
Nyakku Shigure	f88c159de1	[BugFix] Exit if neither modern nor legacy wheel dir not found (#5367) ... --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-12-04 16:45:48 +08:00
SunLei	3697110599	[Docs] update FAQ with logprobs MQ limits and deprecation (#5368) ... * [doc] update FAQ with logprobs MQ limits and deprecation * [doc] update FAQ with logprobs MQ limits and deprecation * update faq	2025-12-04 15:57:04 +08:00
Yonghua Li	f4119d51b4	[PD Disaggregation] support DP via v1 router and decouple DP and EP (#5197) ... * [fix] support DP via v1 router and decouple DP and EP * [fix] fix scripts * [fix] reset model path * [fix] dp use get_output_ep, fix router port type, update scripts * [merge] merge with latest code * [chore] remove some debug log * [fix] fix code style check * [fix] fix test_multi_api_server for log_dir name * [chore] reduce logs * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-12-04 15:38:43 +08:00
Longzhi Wang	5cd17fd662	[Models] Add forward_meta to moe models' forward function (#5138) ... * [Models] Add forward_meta to moe models' forward function * fix missing param * fix * fix * fix forward_meta * fix test and remove chunked MoE releated in config * fix test * fix * fix	2025-12-04 13:26:58 +08:00
Juncai	f5bdb36e9b	Reduce timeout in unittest (#5366)	2025-12-04 13:19:02 +08:00
fmiao2372	209006e6a6	[Intel HPU] fix memory fragmentation issue due to warmup process and fix moe all_reduce issue (#5357)	2025-12-04 11:29:41 +08:00
lizexu123	946025480e	[Bug fix] fix pooling models (#5358) ... * fix * fix * fix test * fix gpu_model_runner --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>	2025-12-04 11:06:30 +08:00
qwes5s5	a52aea073c	fix logprobs (#5335)	2025-12-04 10:38:51 +08:00
Echo-Nie	96ff402d44	[Optimization] Remove version constraints for setuptools, uvicorn, triton and safetensors, del fastsafetensors (#5330) ... * Remove version constraints for setuptools, triton, and fastsafetensors. * remove version for uvicorn * fix according to review	2025-12-04 10:07:31 +08:00
Yuanle Liu	be0c960260	[BugFix] dynamic cache kv block_wise_fp8 not need create layer.cache_k_scale (#5362)	2025-12-03 05:32:59 -08:00
周周周	a36d60aa18	[FIX BUG] fix bug in TP in permute_x_fp8_kernel (#5350) ... * commit * commit * commit * commit * commit * commit	2025-12-03 05:17:37 -08:00