Rob Mulla dd39f91edb

[Doc] cleanup TPU documentation and remove outdated examples (#29048) ...

Signed-off-by: Rob Mulla <rob.mulla@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2025-11-21 00:05:59 +00:00

..

basic

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

disaggregated-prefill-v1

…

kv_load_failure_recovery

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

logits_processor

[Bugfix] Validate custom logits processor xargs for online serving (#27560)

2025-11-05 16:53:33 +00:00

openai_batch

[Doc] ruff format remaining Python examples (#26795)

2025-10-15 01:25:49 -07:00

pooling

[Frontend][Doc][5/N] Improve all pooling task | Polish encode (pooling) api & Document. (#25524)

2025-10-30 12:13:05 +00:00

qwen2_5_omni

[[V0 deprecation]]Remove VLLM_USE_V1 env (#28204)

2025-11-11 18:22:16 -07:00

async_llm_streaming.py

…

audio_language.py

Remove audio optional dependency for mistral-common (#28722)

2025-11-14 09:54:38 -08:00

automatic_prefix_caching.py

…

batch_llm_inference.py

…

chat_with_tools.py

…

context_extension.py

Update rope_scaling to rope_parameters in preparation for Transformers v5 (#28542)

2025-11-19 09:06:36 -08:00

data_parallel.py

[Chore] Separate out vllm.utils.network_utils (#27164)

2025-10-19 03:06:32 -07:00

disaggregated_prefill.py

…

encoder_decoder_multimodal.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

llm_engine_example.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

load_sharded_state.py

[Misc] fix typo and add detailed log (#28178)

2025-11-09 05:33:46 +00:00

lora_with_quantization_inference.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

metrics.py

…

mistral-small.py

…

mlpspeculator.py

[[V0 deprecation]]Remove VLLM_USE_V1 env (#28204)

2025-11-11 18:22:16 -07:00

multilora_inference.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

prefix_caching.py

…

prompt_embed_inference.py

…

qwen_1m.py

Remove V0 attention backends (#25351)

2025-09-21 16:03:28 -07:00

reproducibility.py

…

rlhf_colocate.py

…

rlhf_online_quant.py

Move online quantization to model.load_weights (#26327)

2025-11-18 16:52:41 -08:00

rlhf_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

rlhf.py

Move online quantization to model.load_weights (#26327)

2025-11-18 16:52:41 -08:00

save_sharded_state.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

simple_profiling.py

…

skip_loading_weights_in_engine_init.py

…

spec_decode.py

[chore] Move some wikimedia images to S3 (#28351)

2025-11-09 01:58:26 +00:00

structured_outputs.py

[Chore] Cleanup guided namespace, move to structured outputs config (#22772)

2025-09-18 09:20:27 +00:00

torchrun_dp_example.py

[CI/Build] Test torchrun with 8 cards (#27548)

2025-10-29 10:26:06 -07:00

torchrun_example.py

…

vision_language_multi_image.py

[chore] Move some wikimedia images to S3 (#28351)

2025-11-09 01:58:26 +00:00

vision_language_pooling.py

[chore] Move the rest of wikimedia url to S3 (#28921)

2025-11-18 09:44:18 -08:00

vision_language.py

[Bugfix] Fix FPS value type for Qwen2.5-Omni video processing (#28630)

2025-11-13 13:06:06 +00:00