tzhouam 87a1fd8da2 rebase: adapt to vLLM v0.29 APIs ...

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2026-09-10 00:41:52 +08:00

..

ops

[Perf][Model] Add optimized LTX-2.5 DiffVAE operators (#7308)

2026-09-09 08:31:16 +00:00

vae

[Perf][Model] Add optimized LTX-2.5 DiffVAE operators (#7308)

2026-09-09 08:31:16 +00:00

__init__.py

[Model] Add LTX-2.5 support (#6070)

2026-08-15 18:27:23 +08:00

ltx2_adapter_parser.py

[Feat] LTX Standard Two-Stage Pipeline (#5500)

2026-08-14 00:13:14 +08:00

ltx2_components.py

[Bugfix] Resolve #6931 hub FA3 on torch 2.13 via kernels 0.16.1 (#7185)

2026-09-09 10:20:34 +00:00

ltx2_conditioning.py

[Perf][Model] Optimize LTX video output transport (#7000)

2026-09-04 06:47:28 +00:00

ltx2_denoise.py

[Model][Perf] Optimize LTX Ulysses sequence parallelism (#7079)

2026-09-07 10:48:26 +00:00

ltx2_guidance.py

[Model] Add LTX-2.5 support (#6070)

2026-08-15 18:27:23 +08:00

ltx2_latents.py

[Diffusion] Add LTX-2.5 Diffusion VAE decoder support (#6189)

2026-08-27 23:54:40 +08:00

ltx2_phase_adapter.py

rebase: adapt to vLLM v0.29 APIs

2026-09-10 00:41:52 +08:00

ltx2_recipes.py

[Model] Add LTX-2.5 support (#6070)

2026-08-15 18:27:23 +08:00

ltx2_request.py

[Model][Perf] Optimize LTX Ulysses sequence parallelism (#7079)

2026-09-07 10:48:26 +00:00

ltx2_runtime.py

[Bugfix] Make LTX vocoder decoding deterministic (#7231)

2026-09-09 06:37:01 +00:00

ltx2_sequence_parallel.py

[Model][Perf] Optimize LTX Ulysses sequence parallelism (#7079)

2026-09-07 10:48:26 +00:00

ltx2_transformer.py

[Model][Perf] Optimize LTX Ulysses sequence parallelism (#7079)

2026-09-07 10:48:26 +00:00

pipeline_ltx2_two_stage.py

[Model] Add LTX-2.5 support (#6070)

2026-08-15 18:27:23 +08:00

pipeline_ltx2.py

[Model] Add LTX-2.5 support (#6070)

2026-08-15 18:27:23 +08:00