This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
fec347dee130a79d8a56390ffcb2dde2e480f6ca
vLLM
/
vllm
/
v1
/
spec_decode
T
History
Andrew Xia
79ac59f32e
Update Spec Decode metrics to include drafted and accepted token throughput (
#24127
)
...
Signed-off-by: Andrew Xia <
axia@meta.com
>
2025-09-11 19:58:43 +00:00
..
__init__.py
[V1][BugFix] Add __init__.py to v1/spec_decode/ (
#13359
)
2025-02-16 09:39:08 -08:00
eagle.py
Add the support for the qwen3 next model (a hybrid attention model). (
#24526
)
2025-09-11 15:32:09 +08:00
medusa.py
[Spec Decode] Make
propose_draft_token_ids
non-blocking for lower TTFT (
#23041
)
2025-08-18 17:20:38 -07:00
metadata.py
[Misc] Add SPDX-FileCopyrightText (
#19100
)
2025-06-03 11:20:17 -07:00
metrics.py
Update Spec Decode metrics to include drafted and accepted token throughput (
#24127
)
2025-09-11 19:58:43 +00:00
ngram_proposer.py
[Doc]: fix typos in Python comments (
#24026
)
2025-09-01 09:38:20 +00:00
utils.py
[Attention] Refactor attention metadata builder interface (
#20466
)
2025-07-17 04:44:25 +00:00