-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Pull requests: JustVugg/colibri
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(xdna): optional explicit AMD XDNA2 lane for the GLM shared expert
#1261
opened Aug 28, 2026 by
Kenneth-Javier
Contributor
Loading…
test: isolate tool E2E API key environment
#1259
opened Aug 28, 2026 by
ZacharyZcR
Contributor
Loading…
fix(qwen36): escape quotes in OpenAI JSON
#1258
opened Aug 28, 2026 by
ZacharyZcR
Contributor
Loading…
perf(dsv4): replace ldexpf with arithmetic
#1255
opened Aug 27, 2026 by
TechPizzaDev
Loading…
4 of 5 tasks
fix(cuda): charge the expert tier real VRAM, not logical bytes (#687)
#1244
opened Aug 26, 2026 by
Unknown-Findout
Contributor
Loading…
perf(sse41): add SSE4.1 fallback tier for olmoe and qwen36 int8 GEMV
#1239
opened Aug 26, 2026 by
jtinbergen
Loading…
feat(experiments): validate reproducible performance records
#1238
opened Aug 26, 2026 by
ZacharyZcR
Contributor
Loading…
fix(qwen36): keep CUDA tier heat adaptive
#1237
opened Aug 26, 2026 by
ZacharyZcR
Contributor
Loading…
feat(planner): emit evidence-backed next actions
#1236
opened Aug 26, 2026 by
ZacharyZcR
Contributor
Loading…
fix(telemetry): report Vulkan expert residency
#1235
opened Aug 26, 2026 by
ZacharyZcR
Contributor
Loading…
fix(cuda): pin speculative expert kernel family
#1234
opened Aug 26, 2026 by
ZacharyZcR
Contributor
Loading…
fix(qwen36): widen jb buffers, add size_t casts, fix nested comment
#1232
opened Aug 25, 2026 by
Petsku01
Loading…
build(cuda): NVCC_ALLOW_UNSUPPORTED, so a host compiler newer than VS2022 is reachable
#1231
opened Aug 25, 2026 by
Unknown-Findout
Contributor
Loading…
fix(k3): K3_VALIDATE_OUT defaults to a hardcoded /tmp path
#1230
opened Aug 25, 2026 by
Unknown-Findout
Contributor
Loading…
fix(tools): k3_tokenizer --ctest writes its fixture to a hardcoded /tmp path
#1229
opened Aug 25, 2026 by
Unknown-Findout
Contributor
Loading…
feat(glm52): optimize inference on single RTX 3090 (24GB) via Direct I/O and MTP
#1177
opened Aug 22, 2026 by
up1t3
Loading…
feat: fmt=8 (fp8-e4m3) decode on the kv_b absorb path, CPU and CUDA
#1102
opened Aug 19, 2026 by
monotophic
Contributor
Loading…
fix(doctor,planner): make DeepSeek-V4 checkpoints pass doctor and plan correctly
#1006
opened Aug 14, 2026 by
RobinHoodO
Loading…
cuda: zero-copy expert views on pageable-shared memory (GB10)
#936
opened Aug 11, 2026 by
Nanetnounou
Contributor
Loading…
cuda: warp-per-row E8 kernels, lattice table in shared memory
#935
opened Aug 11, 2026 by
Nanetnounou
Contributor
Loading…
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.