Commit Graph
17 Commits
Author SHA1 Message Date
Shu Wang d35fea1b2b [Nvidia] Add trtllm mnnvl allreduce with unified flashinfer allreduce fusion api (#12787) 2026-03-17 10:02:45 -07:00
Shu Wang 61de303f0a Fix fallback to default tactic (flashinfer autotuner) with trtllm_fp4_block_scale_moe (#19189) 2026-03-06 15:15:04 -08:00
Shu WangandBaizhou Zhang 43bdee703e Fix Fp8 MTP layer a2a backend without EP. (#18515)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
2026-03-04 16:28:10 -08:00
Shu Wang 1b75d0d1a9 Fix BatchMLAPagedAttentionWrapper query/qo_inptr mismatch for EAGLE (#15601) 2026-02-27 11:35:45 -08:00
Shu Wang 5c02217746 Inclusion of nvfp4 blockscale in EPLB Rebalance (#17158) 2026-01-19 17:45:27 +08:00
Shu Wang 665cb02003 Fix regression caused by fa3 block_table (#15009) 2025-12-12 19:11:09 -08:00
Shu Wang a56f770277 Fix global scaling factor loading hang (#13484) 2025-11-21 16:07:06 -08:00
Shu Wang 6664083522 Replace [silu_and_mul_]scaled_fp4_group_quant by Flashinfer equivalent (#12376) 2025-11-13 00:26:00 -08:00
Shu Wang 7aa443903d Fix nan in global scaling factor for large scale nvfp4 EP (#13162) 2025-11-12 15:32:23 -08:00
Shu Wang 82f39dc11d Add mm_fp4 trtllm backend (#12406) 2025-11-05 14:31:46 -08:00
Shu Wang 1ba137e98f Enable trtllm mla prefix extend (#10526) 2025-09-17 16:44:11 -07:00
Shu Wang 124097fc5b enable prefix cache with dp (#10459) 2025-09-16 18:26:58 -07:00
Shu WangandElfie Guo 36acd2ff16 Fix chunked prefix cache for nvfp4 (#10180)
Co-authored-by: Elfie Guo <elfieg@nvidia.com>
2025-09-12 03:20:30 -07:00
Shu Wang 3df05f4d6a [NVIDIA] [3/N] Nvfp4 Masked Gemm: Add flashinfer grouped_gemm_nt_masked (#9199) 2025-09-11 20:18:43 -07:00
Shu Wang 288ae41f7a [NVIDIA] Fix num_experts in modelopt_quant (#8811) 2025-08-06 14:35:07 -07:00
Shu Wang b01eeb80f8 [NVIDIA]Fix local_num_experts for EP (#8779) 2025-08-04 22:01:14 -07:00
Shu Wang ad4e58bf67 Support fp8 gemm for blackwell (#4558) 2025-03-20 12:40:28 -07:00