Issues - Comfy-Org/comfy-aimdo - Forgejo: Beyond coding. We Forge.

Comfy-Org/comfy-aimdo

mirror of https://github.com/Comfy-Org/comfy-aimdo.git synced 2026-11-04 23:37:21 +00:00

Search syntax

`assignee:<username>`	Filter by assigned user
`author:<username>`	Filter by the author
`is:all`	All
`is:closed`	Closed
`is:open`	Open
`mentions:<username>`	Filter by mentioned user
`modified:[>\|<]<date>`	Filter by last modified date
`review:<username>`	Filter by user who reviewed
`sort:<by>:[asc\|desc]`	Sort by: `created\|comments\|updated\|deadline`

New issue

[PR #127] Retry undocumented CUDA NOT_READY from cuMemSetAccess

#128 opened 2026-10-26 22:24:50 +00:00 by bsakaguchi

[PR #98] feat: add clangd compile_commands.json generator script

#116 opened 2026-10-26 22:24:42 +00:00 by bsakaguchi

[PR #72] Added support for MCDM and GPU-PV through the DXCore API

#99 opened 2026-10-26 22:24:33 +00:00 by bsakaguchi 2 / 2

[PR #59] [ROCm] revert chunk size to 16MB

#93 opened 2026-10-26 22:24:29 +00:00 by bsakaguchi 2 / 2

[PR #31] Multi-GPU support: per-device VRAM management

#71 opened 2026-10-26 22:24:18 +00:00 by bsakaguchi

[PR #27] fix: implement ELF GOT patching for CUDA hooks on Linux/WSL2

#70 opened 2026-10-26 22:24:18 +00:00 by bsakaguchi 0 / 2

[GH-ISSUE #131] [ROCm/Linux][gfx1150 APU] DynamicVRAM hangs in lib.vbar_fault(); with --disable-dynamic-vram, mmap-backed safetensors upload at ~6 MB/s

#51 opened 2026-10-26 22:24:04 +00:00 by bsakaguchi

[GH-ISSUE #128] Redundant full-deficit eviction on every allocation causes multi-hour VRAM thrash under sustained oversubscription

#50 opened 2026-10-26 22:24:04 +00:00 by bsakaguchi

[GH-ISSUE #129] malloc graph: a rogue candidate freed before the root pop permanently poisons the graph → RuntimeError("aimdo memory compile error")

#49 opened 2026-10-26 22:24:04 +00:00 by bsakaguchi

[GH-ISSUE #124] [ROCm/Linux][gfx1200 RDNA4] DynamicVRAM hangs forever inside lib.vbar_fault() when materializing int8_convrot text-encoder weights (one core at 100%, VRAM never grows)

#48 opened 2026-10-26 22:24:03 +00:00 by bsakaguchi

[GH-ISSUE #125] malloc_graph_destroy() stack-overflows on deep allocation graphs (Windows 1 MB stack), cleanup aborts, next run crashes with 0xC0000005

#47 opened 2026-10-26 22:24:03 +00:00 by bsakaguchi

[GH-ISSUE #120] [Windows][AMD][ROCm 7.13] Access violation in vrambuf_create() when DynamicVRAM allocates cast buffer (RX 9070 XT)

#45 opened 2026-10-26 22:24:01 +00:00 by bsakaguchi

[GH-ISSUE #117] vbar_fault() resident detection for a VAE degrades irreversibly after a multi-segment continuity generation (26x H2D memcpy blowup, GPU compute unaffected)

#44 opened 2026-10-26 22:24:01 +00:00 by bsakaguchi

[GH-ISSUE #118] Windows, 16 GB GPU, SATA models (fast_disk=False): model start stalls for minutes at 100% util / ~60 W with VRAM pinned at 15.4–15.8 GB after "0 models unloaded" (MiniMax H3)

#43 opened 2026-10-26 22:24:00 +00:00 by bsakaguchi

[GH-ISSUE #112] Windows / RTX 5070 Ti: comfy-aimdo 0.5.3 missing get_simple_vram_headroom after ComfyUI 0.35.0 update; rollback to 0.34.6 works

#41 opened 2026-10-26 22:23:59 +00:00 by bsakaguchi

[GH-ISSUE #114] aimdo.so: undefined symbol: g_cuda - No working comfy-aimdo - torch.jit.script is not supported in Python 3.14+

#40 opened 2026-10-26 22:23:59 +00:00 by bsakaguchi

[GH-ISSUE #101] Possible mismatch between cuGetProcAddress function pointer and driver symbol

#39 opened 2026-10-26 22:23:58 +00:00 by bsakaguchi

[GH-ISSUE #102] incorrect list handling in copy_small_ranges

#38 opened 2026-10-26 22:23:58 +00:00 by bsakaguchi

[GH-ISSUE #100] Blackwell (RTX 5060 Ti): intermittent Fault failed: 2 (cuMemSetAccess: device not ready) with DynamicVRAM/VBAR

#36 opened 2026-10-26 22:23:55 +00:00 by bsakaguchi

[GH-ISSUE #99] [ROCm multi-GPU] account_free uses the current device instead of the allocation owner

#35 opened 2026-10-26 22:23:55 +00:00 by bsakaguchi

1 2 3