[feat] FlashInfer CuteDSL MegaMoE integration (#54049)
Signed-off-by: jdebache <jdebache@nvidia.com>
This commit is contained in:
@@ -56,6 +56,7 @@ All2AllBackend = Literal[
|
||||
"flashinfer_all2allv", # temporary alias for flashinfer_nvlink_two_sided
|
||||
"flashinfer_nvlink_two_sided",
|
||||
"flashinfer_nvlink_one_sided",
|
||||
"passthrough",
|
||||
]
|
||||
|
||||
|
||||
@@ -211,7 +212,10 @@ class ParallelConfig:
|
||||
- "moonep": MoonEP balanced EP with dynamic redundant experts (NVLink)
|
||||
- "nixl_ep": Use nixl-ep kernels
|
||||
- "flashinfer_nvlink_one_sided": Use flashinfer high-throughput a2a kernels
|
||||
- "flashinfer_nvlink_two_sided": Use flashinfer two-sided kernels for mnnvl"""
|
||||
- "flashinfer_nvlink_two_sided": Use flashinfer two-sided kernels for mnnvl
|
||||
- "passthrough": No all2all at all: the MoE backend dispatches and combines
|
||||
itself (e.g. the FlashInfer MoE-EP megakernels). Bound automatically for
|
||||
such MoE backends; not selectable from the CLI."""
|
||||
|
||||
max_parallel_loading_workers: int | None = Field(default=None, ge=1)
|
||||
"""Maximum number of parallel loading workers when loading model
|
||||
@@ -742,6 +746,7 @@ class ParallelConfig:
|
||||
"deepep_low_latency",
|
||||
"deepep_v2",
|
||||
"flashinfer_nvlink_one_sided",
|
||||
"passthrough",
|
||||
"mori_high_throughput",
|
||||
"mori_low_latency",
|
||||
"nixl_ep",
|
||||
|
||||
Reference in New Issue
Block a user