jiahanc 254a7f8fd6

[Perf] Do FP4 quant before All gather on flashinfer trtllmgen MOE (#30014) ...

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>

2025-12-16 13:01:48 -08:00

..

__init__.py

…

all2all.py

[Perf] Do FP4 quant before All gather on flashinfer trtllmgen MOE (#30014)

2025-12-16 13:01:48 -08:00

all_reduce_utils.py

…

base_device_communicator.py

[Perf] Do FP4 quant before All gather on flashinfer trtllmgen MOE (#30014)

2025-12-16 13:01:48 -08:00

cpu_communicator.py

…

cuda_communicator.py

[Perf] Do FP4 quant before All gather on flashinfer trtllmgen MOE (#30014)

2025-12-16 13:01:48 -08:00

cuda_wrapper.py

[Core][AMD] Migrate fully transparent sleep mode to ROCm platform (#12695)

2025-11-12 15:24:12 -08:00

custom_all_reduce.py

…

mnnvl_compat.py

…

pynccl_allocator.py

[Doc]: fixing typos in various files. (#29717)

2025-11-29 01:15:39 -08:00

pynccl_wrapper.py

…

pynccl.py

…

quick_all_reduce.py

…

ray_communicator.py

…

shm_broadcast.py

fix(shm): Add memory barriers for cross-process shared memory visibility (#30407)

2025-12-10 23:01:19 +00:00

shm_object_storage.py

[Bugfix] Missing cached item in the MultiModalReceiverCache (#28525)

2025-12-01 10:18:07 -08:00

symm_mem.py

Revert "[Bugfix] Fix GPT-OSS AR+NORM fusion (#28841)" (#29483)

2025-11-26 22:27:26 +08:00

tpu_communicator.py

[TPU] add tpu_inference (#27277)

2025-11-26 14:46:36 -08:00

xpu_communicator.py

…