-
Notifications
You must be signed in to change notification settings - Fork 2.7k
Pull requests: JustVugg/colibri
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
deepseek_v4: wire tool calling via checkpoint-native DSML encoding
#992
opened Aug 13, 2026 by
gcaponi
Loading…
fix(msys2): use UTF-8 prompt file for DeepSeek V4
#991
opened Aug 13, 2026 by
IgorLalak
Loading…
3 of 5 tasks
cuda: keep async expert slots alive through completion
#989
opened Aug 12, 2026 by
ZacharyZcR
Contributor
Loading…
feat(v4): dual-SSD mirror (COLI_MODEL_MIRROR) for the DeepSeek V4 expert store
#988
opened Aug 12, 2026 by
dcutugno
Contributor
Loading…
inkling: size direct-run OpenMP teams with the shared physical-core helper
#987
opened Aug 12, 2026 by
Blakeolson21
Contributor
Loading…
openai_server: use COLI_TEMP as the gateway default temperature
#986
opened Aug 12, 2026 by
Blakeolson21
Contributor
Loading…
fix(v4): move hot rows16 packing out of store mutex
#983
opened Aug 12, 2026 by
aniketshukla1
Loading…
Kimi K3: run the dense trunk on CUDA during prefill (1.46x prefill, 1.18x end-to-end)
#977
opened Aug 12, 2026 by
pks
Loading…
feat(v4): emit dashboard telemetry (EMAP/HITS/TIERS/PROF/HWINFO)
#973
opened Aug 12, 2026 by
martinm86867-ops
Loading…
feat(v4): the expert history lives in route_trace.h now — #700 completed
#969
opened Aug 12, 2026 by
terrizoaguimor
Contributor
Loading…
fix(build): compile CUDA backend on glibc >= 2.41
#966
opened Aug 11, 2026 by
martinm86867-ops
Loading…
feat(k3): map prepared weights read-only
#965
opened Aug 11, 2026 by
bherald
Contributor
Loading…
12 tasks done
v4: pluggable expert-store backend registry
#964
opened Aug 11, 2026 by
8PotatoChip8
Loading…
3 of 5 tasks
deepseek_v4: let the launchers delegate OpenMP team sizing to the runtime
#958
opened Aug 11, 2026 by
Blakeolson21
Contributor
Loading…
tools: add one-command datapoint runner
#952
opened Aug 11, 2026 by
gouravkargwal
Contributor
Loading…
bench: decode-regime GEMV bandwidth vs the read ceiling, with a frozen A/B baseline
#950
opened Aug 11, 2026 by
terrizoaguimor
Contributor
Loading…
ci: run Metal backend tests on macOS
enhancement
New feature or request
metal
Backend Metal/Apple
#947
opened Aug 11, 2026 by
gouravkargwal
Contributor
Loading…
cuda: zero-copy expert views on pageable-shared memory (GB10)
#936
opened Aug 11, 2026 by
Nanetnounou
Loading…
cuda: warp-per-row E8 kernels, lattice table in shared memory
#935
opened Aug 11, 2026 by
Nanetnounou
Loading…
feat(plan): discover Windows AMD GPUs without planning against them
#931
opened Aug 10, 2026 by
Kenneth-Javier
Contributor
Loading…
4 of 5 tasks
Scan vulkan devices in reverse order, to avoid main GPU
discussion
Proposta / discussione aperta, non un task
vulkan
Backend Vulkan/AMD
#917
opened Aug 10, 2026 by
xxxajk
Loading…
3 of 5 tasks
feat(moe): add DEGRADE_ZERO miss-slot zero-fill policy (issue #865)
enhancement
New feature or request
performance
Velocità / tok-s / ottimizzazioni
quality
Qualità del modello / quantizzazione
#906
opened Aug 9, 2026 by
kritikagarg
Loading…
2 of 5 tasks
fix: report Vulkan expert residency in telemetry and brain map
bug
Difetto verificato nel codice
needs-rebase
Confligge, serve rebase dell'autore
vulkan
Backend Vulkan/AMD
#891
opened Aug 8, 2026 by
MasterCATZ
Loading…
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.