chen 7c1fd19f0f [OPs] MoE support wfp8afp8(channelwise) and improve per_token_quant_fp8 (#4238)

2025-09-24 16:39:51 +08:00

..

graph_optimization

[CUDAGraph] Support multi output buffers and merge some fixes from feature/exp_0908 (#4062)

2025-09-15 16:21:30 +08:00

guided_decoding

[FDConfig]Remove max_num_batched_tokens/max_num_seqs in parallel config (#4116)

2025-09-17 10:43:35 +08:00

layers

[OPs] MoE support wfp8afp8(channelwise) and improve per_token_quant_fp8 (#4238)

2025-09-24 16:39:51 +08:00

model_loader

[v1 loader]code style (#4204)

2025-09-23 19:36:00 +08:00

models

[BugFix] fix qwen3-embedding model tp>1 (#4223)

2025-09-24 14:13:26 +08:00

ops

[Intel HPU] Support intel hpu platform (#4161)

2025-09-24 12:27:50 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

forward_meta.py

[Intel HPU] Support intel hpu platform (#4161)

2025-09-24 12:27:50 +08:00

load_weight_utils.py

[v1 loader]code style (#4204)

2025-09-23 19:36:00 +08:00

pre_and_post_process.py

[Intel HPU] Support intel hpu platform (#4161)

2025-09-24 12:27:50 +08:00

utils.py

[Feature] support pool (#3827)

2025-09-22 14:09:09 +08:00