[MoE] Refine FlashInfer one-sided All2All integration (#51924)

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Bo Li
2026-08-18 00:18:14 +00:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 0db502c8d8
commit c296851a7d
8 changed files with 129 additions and 68 deletions
+1 -1
View File
@@ -130,7 +130,7 @@ BACKEND_SUPPORTED_QUANTS: dict[str, set[str | None]] = {
"mori_high_throughput": {None, "fp8", "modelopt_fp8"},
"mori_low_latency": {None, "fp8", "modelopt_fp8"},
"flashinfer_nvlink_two_sided": {None, "fp8_blocked", "modelopt_fp4"}, # noqa: E501
"flashinfer_nvlink_one_sided": {None, "modelopt_fp4"}, # noqa: E501
"flashinfer_nvlink_one_sided": {None, "fp8_blocked", "modelopt_fp4"}, # noqa: E501
"deepep_low_latency": {None, "fp8_blocked", "modelopt_fp4"}, # noqa: E501
"deepep_high_throughput": {None, "fp8_blocked", "modelopt_fp8", "modelopt_fp4"}, # noqa: E501
"nixl_ep": {None, "fp8_blocked", "modelopt_fp8"},