Files

T

0f8b398158 [watermarking] add context deduplication support to speculative decoding (#56807 )

Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

2026-09-30 12:22:10 -04:00

metrics

[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

model_states

[Perf][MRV2] Allow FULL decode graphs for one-token prompt tails (#58400 )

2026-09-28 12:48:52 -07:00

pool

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

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

sample

[watermarking] add context deduplication support to speculative decoding (#56807 )

2026-09-30 12:22:10 -04:00

spec_decode

[watermarking] add context deduplication support to speculative decoding (#56807 )

2026-09-30 12:22:10 -04:00

__init__.py

…

async_utils.py

[Feature] Add fixed-token prefill scoring (#54335 )

2026-09-28 07:50:09 -07:00

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

[Elastic EP] Support Model Runner V2 (#53934 )

2026-09-29 00:20:40 +00:00

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

[Elastic EP] Support Model Runner V2 (#53934 )

2026-09-29 00:20:40 +00:00

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

[Elastic EP] Support Model Runner V2 (#53934 )

2026-09-29 00:20:40 +00:00

input_batch.py

[Perf][MRV2] Allow FULL decode graphs for one-token prompt tails (#58400 )

2026-09-28 12:48:52 -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

[watermarking] add context deduplication support to speculative decoding (#56807 )

2026-09-30 12:22:10 -04:00

pcp_manager.py

[Feat] Support PP with PCP in GPU Model Runner V2 (#59139 )

2026-09-30 10:21:56 -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

…

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

[Perf][MRV2] Allow FULL decode graphs for one-token prompt tails (#58400 )

2026-09-28 12:48:52 -07:00

warmup.py

[Elastic EP] Support Model Runner V2 (#53934 )

2026-09-29 00:20:40 +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.