Logo
Explore Help
Sign In
iHore/vLLM
Watch 8
Star 0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
Files
3ca00a8261c7790ba7487e2001ab9004ad8065f2
vLLM/vllm/v1/hisparse
T
History
Matthew BonanniandClaude Opus 5.5 e82b80099a [Perf][HiSparse] Cache per-request residency instead of rescanning every page each step (#60083)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 13:04:55 -04:00
..
__init__.py
[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)
2026-09-12 00:36:47 -04:00
binding.py
[Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with a saturated GPU pool (#59309)
2026-10-01 23:04:21 -07:00
block_pool.py
[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)
2026-09-12 00:36:47 -04:00
coordinator.py
[Perf][HiSparse] Cache per-request residency instead of rescanning every page each step (#60083)
2026-10-06 13:04:55 -04:00
layout.py
[HiSparse] Log steady-state max concurrency and expose host-tier utilization gauges (#58949)
2026-10-05 14:20:32 -07:00
runtime.py
[Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with a saturated GPU pool (#59309)
2026-10-01 23:04:21 -07:00
types.py
[HiSparse] Log steady-state max concurrency and expose host-tier utilization gauges (#58949)
2026-10-05 14:20:32 -07:00
Powered by Gitea Version: 1.27.2 Page: 698ms Template: 6ms
Auto
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