Roger Wang 16484d394c [Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475) ...

Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Sun Kim <sunytokki@gmail.com>
(cherry picked from commit f5f51e5931ffd99afe69696b60765b88d3eb13f2)

2025-12-16 17:15:49 -08:00

..

attention

…

core

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)

2025-12-16 17:15:49 -08:00

cudagraph

…

determinism

…

distributed

…

e2e

…

ec_connector

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)

2025-12-16 17:15:49 -08:00

engine

…

entrypoints

fix: Update json features supported by xGrammar (#30390)

2025-12-14 02:16:06 -08:00

executor

…

kv_connector

[NIXL][BUG FIX] Fix a bug for PD with host_buffer after merging 29665 (#30420)

2025-12-14 15:38:28 +00:00

kv_offload

CPU KV Offloading: Use more CUDA streams (#29013)

2025-12-14 23:50:45 +00:00

logits_processors

…

metrics

…

sample

[bugfix] fix bug when top_logprobs=0 with spec decoding (#30059)

2025-12-12 09:03:35 -08:00

shutdown

…

spec_decode

…

structured_output

fix: Update json features supported by xGrammar (#30390)

2025-12-14 02:16:06 -08:00

tpu

…

tracing

…

worker

…

__init__.py

…

test_oracle.py

…

test_outputs.py

…

test_request.py

…

test_serial_utils.py

…

utils.py

…