vLLM/vllm/model_executor at 3f72639d36a15b348c3dfee211daa3da8140736f - vLLM

iHore/vLLM

Fork 0

Files

T

History

3f72639d36 [FIX] Add NO_MUL activation support for modular kernel path (#31528 )

Signed-off-by: dafrimi <dafrimi@nvidia.com>
Signed-off-by: <>
Co-authored-by: root <root@gpu-267.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: root <root@gpu-537.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: root <root@pool0-01777.cm.cluster>

2026-01-12 11:55:49 -05:00

layers

[FIX] Add NO_MUL activation support for modular kernel path (#31528 )

2026-01-12 11:55:49 -05:00

model_loader

[FixBug] Improve exception string in tensorizer.py (#31680 )

2026-01-11 05:01:53 -08:00

models

[MODEL] New model support for kakaocorp/kanana-1.5-v-3b-instruct (#29384 )

2026-01-12 16:39:02 +00:00

warmup

[UX] Reduce DeepGEMM warmup log output to single progress bar (#30903 )