iHore/vLLM

Files

T

History

dd3bc9c72f [Perf][MRV2] Reuse Mamba/GDN metadata across KV cache groups (#58762 )

Signed-off-by: Luca Motz <luca.motz@icloud.com>
Co-authored-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

2026-09-28 04:36:58 +00:00

..

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

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

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

[Bugfix][MRV2] Treat padded prompt tails as spec-decode rows for hybrid models (#58434 )

2026-09-24 18:29:53 -07:00

[Pooling] Support prompt embeddings in MRV2 decoder pooling (#56639 )

2026-09-13 05:49:45 +00:00

[MRV2] Validate MRV2 entrypoint logits processors (#57728 )

2026-09-24 09:07:26 +00:00

[PCP][DCP] Support DCP target model with non-DCP Dspark (#56723 )

2026-09-26 18:12:35 -04:00

__init__.py

GPU Model Runner V2 (#25266 )

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

async_utils.py

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635 )

2026-09-21 10:25:05 +00:00

attn_utils.py

[Perf][MRV2] Reuse Mamba/GDN metadata across KV cache groups (#58762 )

2026-09-28 04:36:58 +00:00

block_table.py

[PCP][DCP] Support DCP target model with non-DCP Dspark (#56723 )

2026-09-26 18:12:35 -04:00

buffer_utils.py

[MRV2] Buffer util simplifications (#56888 )

2026-09-15 20:36:51 +00:00

cp_utils.py

[MRV2] Miscellaneous code cleanup (#57980 )

2026-09-23 01:51:52 -07:00

cudagraph_utils.py

[Spec Decode] Enable Gemma4 DSpark adaptive verification with FlashInfer (#57263 )

2026-09-26 17:01:17 +08:00

dp_utils.py

[Spec Decode] Enable Gemma4 DSpark adaptive verification with FlashInfer (#57263 )

2026-09-26 17:01:17 +08:00

ec_connector.py

[MRV2] Miscellaneous code cleanup (#57980 )

2026-09-23 01:51:52 -07:00

eplb_utils.py

[MRV2] Miscellaneous code cleanup (#57980 )

2026-09-23 01:51:52 -07:00

input_batch.py

Revert "[DSpark] Support pipeline-parallel targets in aggregated serving (#56956 )" (#58484 )

2026-09-24 08:48:36 -07:00

kv_connector.py

[Bugfix][KVConnector] Finalize saves on steps without a forward (#57775 )

2026-09-25 00:06:36 +00:00

lora_utils.py

Add pydocstyle to the ruff rules (#52136 )

2026-09-16 16:44:29 +00:00

model_runner.py

[PCP][DCP] Support DCP target model with non-DCP Dspark (#56723 )

2026-09-26 18:12:35 -04:00

pcp_manager.py

[PCP][DCP] Support DCP target model with non-DCP Dspark (#56723 )

2026-09-26 18:12:35 -04:00

pp_utils.py

[PP][XPU]Add the flag to control microbatch feature on MRV2+PP (#55145 )

2026-09-25 12:05:35 +08:00

README.md

GPU Model Runner V2 (#25266 )

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

shutdown.py

[MRV2] Add shutdown() method (#41297 )

2026-05-02 21:06:30 -07:00

states.py

[MRV2] Miscellaneous code cleanup (#57980 )

2026-09-23 01:51:52 -07:00

structured_outputs.py

[MRV2] Buffer util simplifications (#56888 )

2026-09-15 20:36:51 +00:00

ubatch_utils.py

[MRV2] Miscellaneous code cleanup (#57980 )

2026-09-23 01:51:52 -07:00

warmup.py

Revert "[DSpark] Support pipeline-parallel targets in aggregated serving (#56956 )" (#58484 )

2026-09-24 08:48:36 -07:00

README.md

[Experimental] Model Runner V2

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