Zhengxu Chen 6173682b6e

[compile] Include enable_sleep_mode into caching factors. (#29696) ...

Signed-off-by: zhxchen17 <zhxchen17@fb.com>

2025-11-29 07:58:38 +08:00

..

__init__.py

[Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233)

2025-11-11 18:58:33 -08:00

cache.py

[caching] Add enable_prompt_embeds and cpu_offload_gb to compile hashes. (#29435)

2025-11-25 21:46:41 +00:00

compilation.py

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): Set up -O infrastructure (#26847)

2025-11-27 01:55:58 -08:00

device.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

ec_transfer.py

[Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233)

2025-11-11 18:58:33 -08:00

kv_events.py

…

kv_transfer.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

load.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

lora.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

model.py

[compile] Include enable_sleep_mode into caching factors. (#29696)

2025-11-29 07:58:38 +08:00

multimodal.py

[Attention] Update attention imports (#29540)

2025-11-27 11:19:09 -05:00

observability.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

parallel.py

[Doc]: fixing typos in diverse files (#29492)

2025-11-27 07:15:50 -08:00

pooler.py

Improve enable chunked_prefill & prefix_caching logic. (#26623)

2025-11-27 22:05:48 -08:00

scheduler.py

[Deprecation] Advance deprecation status (#29617)

2025-11-27 19:04:58 +00:00

speculative.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

speech_to_text.py

…

structured_outputs.py

[Misc] Add backup hash algorithm for FIPS constrained environments (#28795)

2025-11-26 00:50:22 +00:00

utils.py

[torch.compile] caching of config fields should be opt-out by default (#26468)

2025-11-19 06:13:54 -08:00

vllm.py

[Frontend] Remap -O to -cc commandline flag (#29557)

2025-11-28 21:51:12 +00:00