Fynn Schmitt-Ulms 9433acb8df [Spec Decode] Add hidden states extraction system (#33736) ...

Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>

2026-03-02 14:29:09 -05:00

..

basic

[UX] Use gguf repo_id:quant_type syntax for examples and docs (#33371)

2026-01-31 12:14:54 +08:00

disaggregated-prefill-v1

…

kv_load_failure_recovery

[PD] Change kv_load_failure_policy Default from "recompute" to "fail" (#34896)

2026-02-21 01:34:57 -08:00

logits_processor

…

new_weight_syncing

[Feat][RL][2/2] Native Weight Syncing API: IPC (#34171)

2026-02-27 13:45:21 -07:00

openai_batch

[Docs] Improve documentation (#33799)

2026-02-06 12:57:09 +00:00

qwen2_5_omni

…

qwen3_omni

…

async_llm_streaming.py

…

audio_language.py

…

automatic_prefix_caching.py

…

batch_llm_inference.py

…

chat_with_tools.py

…

context_extension.py

…

data_parallel.py

…

disaggregated_prefill.py

…

encoder_decoder_multimodal.py

…

extract_hidden_states.py

[Spec Decode] Add hidden states extraction system (#33736)

2026-03-02 14:29:09 -05:00

llm_engine_example.py

…

llm_engine_reset_kv.py

…

load_sharded_state.py

…

lora_with_quantization_inference.py

…

metrics.py

…

mistral-small.py

[Doc] Update usage of --limit-mm-per-prompt (#34148)

2026-02-09 21:12:13 -08:00

mlpspeculator.py

…

multilora_inference.py

…

pause_resume.py

[Feat][RL] Pause and Resume with keep requests for single engine (#32351)

2026-02-07 00:08:58 +00:00

prefix_caching.py

…

prompt_embed_inference.py

Explicitly set return_dict for apply_chat_template (#33372)

2026-01-30 07:27:04 +00:00

qwen_1m.py

…

reproducibility.py

…

rlhf_colocate.py

…

rlhf_online_quant.py

…

rlhf_utils.py

…

rlhf.py

…

run_one_batch.py

[Misc] Add run one batch script that supports profiling (#32968)

2026-02-10 18:29:49 -08:00

save_sharded_state.py

…

simple_profiling.py

…

skip_loading_weights_in_engine_init.py

…

spec_decode.py

[Bugfix] Fix --trust-remote-code conflict (#34218)

2026-02-10 00:29:10 -08:00

structured_outputs.py

…

torchrun_dp_example.py

…

torchrun_example.py

…

vision_language_multi_image.py

[Model] Use mm_position to compute mrope positions for GLM-4.xV (#33039)

2026-02-02 16:55:48 +00:00

vision_language.py

[Models] Intern-S1-Pro (#33636)

2026-02-03 05:49:45 -08:00