Nick Hillandrshaw@neuralmagic.com <robertgshaw2@gmail.com> 9d72daf4ce [V1][Perf] Simpler request output queues (#15156) ...

Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>

2025-03-24 22:44:08 +00:00

..

attention

[V1] Enable V1 Fp8 cache for FA3 in the oracle (#15191)

2025-03-23 15:07:04 -07:00

core

[V1] Aggregate chunked prompt logprobs in model runner (#14875)

2025-03-24 12:27:57 -04:00

engine

[V1][Perf] Simpler request output queues (#15156)

2025-03-24 22:44:08 +00:00

executor

[v1] Refactor KVCacheConfig (#14079)

2025-03-21 04:56:27 -07:00

metrics

[V1] Aggregate chunked prompt logprobs in model runner (#14875)

2025-03-24 12:27:57 -04:00

sample

[V1][Minor] fix comments (#15392)

2025-03-24 08:45:32 -07:00

spec_decode

[V1][Spec Decode] Respect prompt_lookup_max (#15348)

2025-03-23 10:41:44 -07:00

stats

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

structured_output

[V1] Add disable-any-whitespace option support for xgrammar (#15316)

2025-03-22 15:56:17 +00:00

worker

[V1] Aggregate chunked prompt logprobs in model runner (#14875)

2025-03-24 12:27:57 -04:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

kv_cache_interface.py

[v1] Refactor KVCacheConfig (#14079)

2025-03-21 04:56:27 -07:00

outputs.py

[V1] Aggregate chunked prompt logprobs in model runner (#14875)

2025-03-24 12:27:57 -04:00

request.py

[V1][Minor] Minor code cleanup for scheduling metrics (#14800)

2025-03-14 08:21:28 +00:00

serial_utils.py

[V1] Use msgpack for core request serialization (#12918)

2025-02-10 11:35:56 +08:00

utils.py

[V1][Minor] Add __repr__ to ConstantList (#14907)

2025-03-16 20:20:15 -07:00