Daniel Hiltgen
|
3518aaef33
Merge pull request #4218 from dhiltgen/auto_parallel
|
10 ヶ月 前 |
Blake Mizerany
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
10 ヶ月 前 |
Daniel Hiltgen
|
9929751cc8
Disable concurrency for AMD + Windows
|
10 ヶ月 前 |
Daniel Hiltgen
|
17b7186cd7
Enable concurrency by default
|
1 年間 前 |
Daniel Hiltgen
|
6f351bf586
review comments and coverage
|
11 ヶ月 前 |
Daniel Hiltgen
|
ff4f0cbd1d
Prevent multiple concurrent loads on the same gpus
|
11 ヶ月 前 |
Daniel Hiltgen
|
fc37c192ae
Refine CPU load behavior with system memory visibility
|
11 ヶ月 前 |
Daniel Hiltgen
|
434dfe30c5
Reintroduce nvidia nvml library for windows
|
11 ヶ月 前 |
Daniel Hiltgen
|
48702dd149
Harden unload for empty runners
|
11 ヶ月 前 |
Daniel Hiltgen
|
5e8ff556cb
Support forced spreading for multi GPU
|
1 年間 前 |
Michael Yang
|
e40145a39d
lint
|
11 ヶ月 前 |
Michael Yang
|
c895a7d13f
some gocritic
|
11 ヶ月 前 |
Michael Yang
|
04f3c12bb7
replace x/exp/slices with slices
|
11 ヶ月 前 |
Patrick Devine
|
4cc3be3035
Move envconfig and consolidate env vars (#4608)
|
11 ヶ月 前 |
Sang Park
|
4434d7f447
Correct typo in error message (#4535)
|
11 ヶ月 前 |
Daniel Hiltgen
|
ec231a7923
Remove VRAM convergence check for windows
|
11 ヶ月 前 |
Patrick Devine
|
6845988807
Ollama `ps` command for showing currently loaded models (#4327)
|
11 ヶ月 前 |
Daniel Hiltgen
|
4142c3ef7c
Always use the sorted list of GPUs
|
11 ヶ月 前 |
Jeffrey Morgan
|
bb6fd02298
Don't clamp ctx size in `PredictServerFit` (#4317)
|
11 ヶ月 前 |
Daniel Hiltgen
|
354ad9254e
Wait for GPU free memory reporting to converge
|
11 ヶ月 前 |
Jeffrey Morgan
|
c9f98622b1
Skip scheduling cancelled requests, always reload unloaded runners (#4189)
|
1 年間 前 |
Jeffrey Morgan
|
dfa2f32ca0
unload in critical section (#4187)
|
1 年間 前 |
Daniel Hiltgen
|
f56aa20014
Centralize server config handling
|
1 年間 前 |
Jeffrey Morgan
|
942c979232
allocate a large enough kv cache for all parallel requests (#4162)
|
1 年間 前 |
Daniel Hiltgen
|
20f6c06569
Make maximum pending request configurable
|
1 年間 前 |
Mark Ward
|
63c763685f
log when the waiting for the process to stop to help debug when other tasks execute during this wait.
|
1 年間 前 |
Mark Ward
|
f4a73d57a4
fix runner expire during active use. Clearing the expire timer as it is used. Allowing the finish to assign an expire timer so that the runner will expire after no use.
|
1 年間 前 |
Daniel Hiltgen
|
d6e3b64582
Fix concurrency for CPU mode
|
1 年間 前 |
Daniel Hiltgen
|
9b5a3c5991
Merge pull request #3914 from dhiltgen/mac_perf
|
1 年間 前 |
Jeffrey Morgan
|
00b0699c75
Reload model if `num_gpu` changes (#3920)
|
1 年間 前 |