OpenSource/ollama

作者	SHA1 備註	提交日期
Daniel Hiltgen	354ad9254e Wait for GPU free memory reporting to converge	11 月之前
Jeffrey Morgan	c9f98622b1 Skip scheduling cancelled requests, always reload unloaded runners (#4189)	1 年之前
Jeffrey Morgan	dfa2f32ca0 unload in critical section (#4187)	1 年之前
Daniel Hiltgen	f56aa20014 Centralize server config handling	1 年之前
Jeffrey Morgan	942c979232 allocate a large enough kv cache for all parallel requests (#4162)	1 年之前
Daniel Hiltgen	20f6c06569 Make maximum pending request configurable	1 年之前
Mark Ward	63c763685f log when the waiting for the process to stop to help debug when other tasks execute during this wait.	1 年之前
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 年之前
Daniel Hiltgen	d6e3b64582 Fix concurrency for CPU mode	1 年之前
Daniel Hiltgen	9b5a3c5991 Merge pull request #3914 from dhiltgen/mac_perf	1 年之前
Jeffrey Morgan	00b0699c75 Reload model if `num_gpu` changes (#3920)	1 年之前
Daniel Hiltgen	b123be5b71 Adjust context size for parallelism	1 年之前
Bryce Reitano	36a6daccab Restructure loading conditional chain	1 年之前
Bryce Reitano	284e02bed0 Move ggml loading to when we attempt fitting	1 年之前
Daniel Hiltgen	34b9db5afc Request and model concurrency	1 年之前