Chenguang Zheng d765cf01fe

[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding sharing between requests (#22711) ...

Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

2025-08-25 00:41:17 -07:00

..

attention

Feature/mla tests (#23195)

2025-08-20 21:46:47 +00:00

core

[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding sharing between requests (#22711)

2025-08-25 00:41:17 -07:00

cudagraph

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

e2e

[CI] Add end-to-end V1 min_tokens test coverage (#22495)

2025-08-21 22:04:07 -06:00

engine

[Misc] Support passing multiple request ids at once to AsyncLLM.abort() (#22944)

2025-08-15 17:00:36 -07:00

entrypoints

Frontend: Adding LM Format Enforcer support to V1 engine (#22564)

2025-08-24 19:31:22 -07:00

executor

[Core] Support custom executor qualname (#23314)

2025-08-22 09:40:54 +08:00

kv_connector

[P/D][Nixl] Make kv cache register compatible with hybrid memory allocator (#23079)

2025-08-21 22:30:48 -07:00

logits_processors

[V1] Logits processors extensibility (#19912)

2025-08-16 12:59:17 -07:00

metrics

Enable v1 metrics tests (#20953)

2025-07-20 03:22:02 +00:00

sample

[Sampler] Support returning final logprobs (#22387)

2025-08-20 21:28:32 -07:00

shutdown

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

spec_decode

[Misc] Add max_seq_len to CommonAttentionMetadata (#23216)

2025-08-20 09:05:29 -07:00

structured_output

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

tpu

[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding sharing between requests (#22711)

2025-08-25 00:41:17 -07:00

worker

[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding sharing between requests (#22711)

2025-08-25 00:41:17 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_async_llm_dp.py

Deprecate --disable-log-requests and replace with --enable-log-requests (#21739)

2025-08-01 17:16:37 +01:00

test_external_lb_dp.py

[Tests] Harden DP tests (#21508)

2025-07-25 02:27:24 -07:00

test_hybrid_lb_dp.py

[Tests] Harden DP tests (#21508)

2025-07-25 02:27:24 -07:00

test_internal_lb_dp.py

[BugFix] Fix port lookup in internal DP LB tests (#22252)

2025-08-15 11:17:11 +08:00

test_kv_sharing.py

Support multiple attention groups for KV sharing (#22672)

2025-08-15 16:54:10 -07:00

test_metrics_reader.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_oracle.py

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

test_request.py

[Misc] Add SPDX-FileCopyrightText (#20428)

2025-07-04 07:40:42 +00:00

test_serial_utils.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

test_utils.py

Support encoder-only models without KV-Cache (#21270)

2025-07-26 21:09:52 +08:00