-
Notifications
You must be signed in to change notification settings - Fork 395
Pull requests: InternLM/xtuner
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Fix] grad_norm_dtype only support float32 and float64
#1402
by jayhenry
was merged Dec 30, 2025
Loading…
[Fix] add abort before offload and fix routed_experts is None
#1394
by YanhuiDua
was merged Dec 29, 2025
Loading…
[Patch] Skip calculating loss of empty
<think></think> (ಥ﹏ಥ)
#1387
by HAOCHENYE
was merged Dec 24, 2025
Loading…
[Fix] add printing token-level entropy and fix get_model_config_from_hf in example config
#1384
by YanhuiDua
was merged Dec 24, 2025
Loading…
[Fix] npu resources scripts and torch_compile_cfg
#1383
by CyCle1024
was merged Dec 29, 2025
Loading…
[Fix] warmup communication right after init process group.
#1380
by CyCle1024
was merged Dec 22, 2025
Loading…
[Bug] fix bugs related to passing torch.dtype to FSDPConfig
#1375
by HIT-cwh
was merged Dec 18, 2025
Loading…
add default lmdeploy/memory/ray log dir in RL scripts
#1374
by YanhuiDua
was merged Dec 22, 2025
Loading…
[CI] update unittest image to fix deep_gemm import error
#1368
by CyCle1024
was merged Dec 18, 2025
Loading…
[Build] fix deep_geem injection by freezing sgl-kernel version
#1367
by CyCle1024
was merged Dec 16, 2025
Loading…
[Enhance] export LoadCheckpointConfig from xtuner.v1.train
#1364
by nil0x9
was merged Dec 18, 2025
Loading…
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.