10 Commits
Author SHA1 Message Date
王鹤男andMick f8f501f2e8 [diffusion] fix: fix nvfp4 diffusion models on sm_120 (RTX PRO 6000 / RTX 50xx) (#35739)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-08-29 14:42:49 +08:00
王鹤男 932f632158 [diffusion] fix: do not warn that the recommended short edge is unverified (#35745) 2026-08-21 22:56:03 +08:00
王鹤男 5ecd6d794d [diffusion] fix: fix quantized qkv scales and missing-param policy for minimax-h3 (#35740) 2026-08-21 22:10:50 +08:00
8389d79e43 ci: add LongCat-Flash-Lite-FP8 8-GPU nightly test + fix NextN rope_theta (#32125)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
2026-07-24 19:45:28 +08:00
b13abfdedf Fix LongCat n-gram token-table crashes on padded batches (#31312)
Co-authored-by: whn09 <whn09@users.noreply.github.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
2026-07-22 20:24:21 +08:00
王鹤男andwhn09 1843384c7a Fix LongCat-2.0 real EP (deepep): double all-reduce + ScMoE RoPE crash (#31311)
Co-authored-by: whn09 <whn09@users.noreply.github.com>
2026-07-20 13:37:16 +08:00
5cbea10e2f Fix LongCat n-gram embedding in PD-disaggregated scheduler loops (#31134)
Co-authored-by: whn09 <whn09@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 15:42:51 +08:00
0a64139c94 Fix --moe-a2a-backend silently ignored for LongCat-2.0 (moe_topk missing from gate) (#30975)
Co-authored-by: whn09 <whn09@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 14:40:01 +08:00
王鹤男 29d23e198f [diffusion] fix: preserve _explicit_fields across dataclasses.replace in DiffGenerator (#25308) 2026-06-04 11:02:23 +08:00
王鹤男andwhn09 5850aa14c3 fix(mooncake): honour MOONCAKE_PROTOCOL so EFA hardware can select efa transport (#25083)
Co-authored-by: whn09 <whn09@users.noreply.github.com>
2026-05-29 14:21:15 +08:00