This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
23b899a8e62c7ea07981bf8487b0dc2cb17847b8
vLLM
/
vllm
/
model_executor
/
layers
/
fused_moe
T
History
bnellnm
eca2c5f7c0
[Bugfix] Fix support for dimension like integers and ScalarType (
#9299
)
2024-10-17 19:08:34 +00:00
..
configs
[Kernel] adding fused moe kernel config for L40S TP4 (
#9245
)
2024-10-11 08:54:22 -07:00
__init__.py
[Misc] Fused MoE Marlin support for GPTQ (
#8217
)
2024-09-09 23:02:52 -04:00
fused_marlin_moe.py
[Bugfix] Fix support for dimension like integers and ScalarType (
#9299
)
2024-10-17 19:08:34 +00:00
fused_moe.py
[Misc] log when using default MoE config (
#8971
)
2024-10-03 04:31:07 +00:00
layer.py
[torch.compile] Fine-grained CustomOp enabling mechanism (
#9300
)
2024-10-17 18:36:37 +00:00
moe_pallas.py
[Hardware][TPU] Support MoE with Pallas GMM kernel (
#6457
)
2024-07-16 09:56:28 -07:00