iHore/vLLM

Files

T

History

Wentao Yeandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 8f87eb4622 [Refactor] Clean up log once scope="local" (#40540 )

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

2026-04-22 16:42:43 -04:00

..

[Model Runner V2] Support num NaNs in logits (#30187 )

2025-12-09 10:00:49 -08:00

[Core] Simplify multimodal masking (#34246 )

2026-04-01 01:18:22 -07:00

[Model Runner V2] Support Streaming Inputs (#37028 )

2026-03-20 20:42:25 +00:00

[Frontend] Re-enable running MaxSim on GPU (#38620 )

2026-04-03 00:03:13 +08:00

[Model Runner V2] Multiple prompt logprobs support (#39937 )

2026-04-21 15:49:05 +00:00

[Model Runner V2][BugFix] fix num_sampled dtype for probabilistic rej… (#39951 )

2026-04-15 18:09:11 -07:00

__init__.py

GPU Model Runner V2 (#25266 )

2025-11-21 08:20:55 -08:00

async_utils.py

[BugFix][MRV2] Fix cuda event reuse race (#39115 )

2026-04-07 00:21:09 +00:00

attn_utils.py

[Model Runner V2] support auto resolve cudagraph mode/sizes based on attn backend (#32936 )

2026-04-10 08:27:15 -07:00

block_table.py

[MRV2] Avoid recompilation of _gather_block_tables_kernel (#37645 )

2026-03-20 10:31:45 -07:00

buffer_utils.py

[V1] Remove pin_memory() in async_copy_to_gpu to fix sporadic stalls (#37006 )

2026-03-14 01:37:32 +00:00

cp_utils.py

[Model Runner V2] Minor simplification for DCP (#34786 )

2026-02-18 11:04:53 -08:00

cudagraph_utils.py

[Model Runner V2][Minor] Simplify PP logic (#38031 )

2026-03-24 13:57:17 -07:00

dp_utils.py

[Model Runner V2] support auto resolve cudagraph mode/sizes based on attn backend (#32936 )

2026-04-10 08:27:15 -07:00

eplb_utils.py

[Refactor] Clean up log once scope="local" (#40540 )

2026-04-22 16:42:43 -04:00

input_batch.py

[Model Runner V2] Do not initialize sampler for non-last PP ranks (#36824 )

2026-03-12 03:55:28 +00:00

kv_connector.py

[MRV2][KVConnector] Fix missing build_connector_worker_meta (#38698 )

2026-04-03 08:42:52 +03:00

lora_utils.py

[ModelRunner V2] Misc minor simplifications and optimizations (#33467 )

2026-02-01 22:17:14 +00:00

model_runner.py

Gate SSU dispatch setup (#40039 )

2026-04-16 13:06:01 -07:00

pp_utils.py

[Model Runner V2] A bit more PP simplification (#34766 )

2026-02-17 21:39:07 -08:00

README.md

GPU Model Runner V2 (#25266 )

2025-11-21 08:20:55 -08:00

states.py

[MRv2]fix: model accuracy regression caused by reusing the stale last_sampled_tokens and draft_tokens (#39833 )

2026-04-21 16:30:32 +00:00

structured_outputs.py

[ModelRunner V2] Misc minor simplifications and optimizations (#33467 )

2026-02-01 22:17:14 +00:00

warmup.py

[MRV2] Consider spec decoding in warmup (#37812 )

2026-03-23 17:45:43 +00:00

README.md

[Experimental] Model Runner V2

This directory contains the new model runner which is under active development. Ping Woosuk Kwon for any changes.