Logo
Explore Help
Register Sign In
EngineX/xc-llm-ascend
3
0
Fork 0
You've already forked xc-llm-ascend
Code Issues Pull Requests Projects Releases Wiki Activity
Files
4e3919e965f531a2ac8343821fdf5f1f617911ad
xc-llm-ascend/vllm_ascend/spec_decode
History
wangxiyuan 4e3919e965 Reapply "[Refactor] Unify full-graph parameter update logic (#6041)" (#6227) (#6231)
This reverts commit 95649344aa.

The CI failure doesn't related to this change. Let's reapply it.

- vLLM version: v0.14.0
- vLLM main:
d68209402d
2026-01-26 09:04:54 +08:00
..
__init__.py
Add Medusa speculative decoding support for vllm_ascend (#5668)
2026-01-23 14:14:23 +08:00
eagle_proposer.py
Reapply "[Refactor] Unify full-graph parameter update logic (#6041)" (#6227) (#6231)
2026-01-26 09:04:54 +08:00
interface.py
Add Medusa speculative decoding support for vllm_ascend (#5668)
2026-01-23 14:14:23 +08:00
medusa_proposer.py
Add Medusa speculative decoding support for vllm_ascend (#5668)
2026-01-23 14:14:23 +08:00
mtp_proposer.py
[Misc] Remove CP Redundant Variables after FIA operator enables for CANN 8.5 (#6013)
2026-01-23 14:13:12 +08:00
ngram_proposer.py
[Bugfix] Fix in_profile_run in mtp_proposer dummy_run (#5165)
2025-12-18 22:27:47 +08:00
suffix_proposer.py
[Bugfix] Fix in_profile_run in mtp_proposer dummy_run (#5165)
2025-12-18 22:27:47 +08:00
Powered by Gitea Version: 1.24.3 Page: 445ms Template: 7ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API