Chen Zhang 24e6ad3f16

[V1] Remove num_input_tokens from attn_metadata (#17193) ...

Signed-off-by: Chen Zhang <zhangch99@outlook.com>

2025-04-29 09:28:41 -07:00

..

attention

[V1] Remove num_input_tokens from attn_metadata (#17193)

2025-04-29 09:28:41 -07:00

core

[V1][Spec Decode] Make eagle compatible with prefix caching. (#17137)

2025-04-27 09:29:43 -07:00

engine

[Misc] Move config fields to MultiModalConfig (#17343)

2025-04-29 06:37:21 +00:00

executor

[BugFix] Remove default multiproc executor collective_rpc timeout (#17000)

2025-04-22 23:27:14 +00:00

metrics

[Metrics] Fix minor inconsistencies in bucket progression (#17262)

2025-04-27 16:19:39 +00:00

sample

[V1][Spec Decode] Always use argmax for sampling draft tokens (#16899)

2025-04-23 14:57:43 -07:00

spec_decode

[V1][Spec Decode] Make Eagle model arch config driven (#17323)

2025-04-29 10:22:02 +08:00

stats

Update deprecated Python 3.8 typing (#13971)

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

structured_output

implement Structural Tag with Guidance backend (#17333)

2025-04-29 02:21:32 +00:00

worker

[V1] Remove num_input_tokens from attn_metadata (#17193)

2025-04-29 09:28:41 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

kv_cache_interface.py

[V1] Implement sliding window attention in kv_cache_manager (#14097)

2025-04-01 00:33:17 -07:00

outputs.py

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

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

request.py

[Core] Remove prompt string from engine core data structures (#17214)

2025-04-25 23:41:05 -07:00

serial_utils.py

Serialize tensors using int8 views (#16866)

2025-04-19 10:28:34 -07:00

utils.py

[V1] Move usage stats to worker and start logging TPU hardware (#16211)

2025-04-25 14:06:01 -06:00