mirror of
https://github.com/AlexsJones/llmfit.git
synced 2026-10-14 20:11:49 +00:00
fix(update): detect MoE models from config.json expert counts (#1142)
#97 -Commit
fa80482e0f
pushed by
vrr
chore(deps): bump jsonschema from 0.55.0 to 0.58.1 (#1139)
#95 -Commit
e897fa5062
pushed by
vrr
fix(plan): grade paths and upgrade deltas with fit's thresholds (#1125)
#93 -Commit
4b9fdd9c5d
pushed by
vrr
chore(deps): bump signpath/github-action-submit-signing-request (#1076)
#89 -Commit
02af06cb07
pushed by
vrr
perf(tui): optimize model search filtering in apply_filters for 40%+ speedup (#934)
#75 -Commit
ca864d0977
pushed by
vrr
feat(cli): add --memory-percent and --ram-percent overrides (#1089)
#73 -Commit
17d45bd667
pushed by
vrr
data: community benchmark (nvidia-geforce-gtx-1080-ti) (#1079)
#67 -Commit
7f47fca32c
pushed by
vrr
bench: community results for nvidia-geforce-gtx-1080-ti (#1078)
#64 -Commit
2ffe4fd899
pushed by
vrr
fix(bench): ignore implausible tok/s from degenerate Ollama timings (#1042)
#54 -Commit
86a0d08a9f
pushed by
vrr
feat(storage): add disk planning for model libraries (#1023)
#52 -Commit
42c2641b75
pushed by
vrr
feat(concurrency): concurrent-session capacity estimator (#140) (#999)
#45 -Commit
1936acc7fb
pushed by
vrr
chore(deps): bump the cargo-minor-patch group with 2 updates (#1005)
#42 -Commit
dc9a8cca2c
pushed by
vrr
chore(deps): bump jsonschema from 0.49.9 to 0.51.0 (#1006)
#35 -Commit
abb13601c3
pushed by
vrr
bench: community results for nvidia-geforce-gtx-1650-with-max-q-design (#985)
#22 -Commit
97451eb548
pushed by
vrr
feat: add --llama-cpp-path global CLI flag mirroring LLAMA_CPP_PATH env var (#583)
#16 -Commit
3222da59b8
pushed by
vrr
docs: sync Chinese README with 1.0 restructured documentation (#982)
#14 -Commit
682aa71de7
pushed by
vrr