Flex Wang 18445edd0f

[Misc] Change buckets of histogram_iteration_tokens to [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8096] to represent number of tokens (#17033) ...

Signed-off-by: sfc-gh-zhwang <flex.wang@snowflake.com>

2025-04-27 12:30:53 +00:00

..

attention

[Bugfix] Get a specific type of layer from forward context (#17222)

2025-04-27 00:58:05 -07:00

core

[MISC] rename interval to max_recent_requests (#14285)

2025-04-26 16:59:18 +00:00

engine

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

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

executor

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

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

metrics

[Misc] Change buckets of histogram_iteration_tokens to [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8096] to represent number of tokens (#17033)

2025-04-27 12:30:53 +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] EAGLE-3 Support (#16937)

2025-04-25 15:43:07 -07:00

stats

Update deprecated Python 3.8 typing (#13971)

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

structured_output

[V1] Add structural_tag support using xgrammar (#17085)

2025-04-26 14:06:37 +00:00

worker

[Bugfix] Get a specific type of layer from forward context (#17222)

2025-04-27 00:58:05 -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