Khushali Desai 23ab0cfdbc speculative decoding under tensor parallelism (TP>1) , workspace creation select max hidden dim of target and draft model (#52193) ...

Signed-off-by: khushali9 <khushali.desai9@gmail.com>

2026-08-24 21:33:36 +00:00

..

__init__.py

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731)

2026-02-06 04:19:49 -08:00

test_async_tp.py

[CI/Build] Use file rendezvous for local distributed tests (#51652)

2026-08-12 10:48:12 +08:00

test_fusion_all_reduce.py

speculative decoding under tensor parallelism (TP>1) , workspace creation select max hidden dim of target and draft model (#52193)

2026-08-24 21:33:36 +00:00

test_sequence_parallelism.py

[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

2026-05-01 23:41:15 -04:00