baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Fix OLLAMA_LLM_LIBRARY with wrong map name and add more env vars to help message (#4663)

Browse source 
* envconfig/config.go: Fix wrong description of OLLAMA_LLM_LIBRARY

Signed-off-by: Lei Jitang <leijitang@outlook.com>

* serve: Add more env to help message of ollama serve

Add more enviroment variables to `ollama serve --help`
to let users know what can be configurated.

Signed-off-by: Lei Jitang <leijitang@outlook.com>

---------

Signed-off-by: Lei Jitang <leijitang@outlook.com>
This commit is contained in:
Lei Jitang 2024-05-31 00:36:51 +08:00 committed by GitHub
parent 96bc232b43
commit a03be18189
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 6 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
cmd/cmd.go
View file

@ -1251,6 +1251,9 @@ func NewCLI() *cobra.Command {
envVars["OLLAMA_NOPRUNE"], envVars["OLLAMA_NOPRUNE"],
envVars["OLLAMA_ORIGINS"], envVars["OLLAMA_ORIGINS"],
envVars["OLLAMA_TMPDIR"], envVars["OLLAMA_TMPDIR"],
envVars["OLLAMA_FLASH_ATTENTION"],
envVars["OLLAMA_LLM_LIBRARY"],
envVars["OLLAMA_MAX_VRAM"],
}) })
default: default:
appendEnvDocs(cmd, envs) appendEnvDocs(cmd, envs)

6
envconfig/config.go
View file

@ -51,16 +51,16 @@ func AsMap() map[string]EnvVar {
"OLLAMA_FLASH_ATTENTION": {"OLLAMA_FLASH_ATTENTION", FlashAttention, "Enabled flash attention"}, "OLLAMA_FLASH_ATTENTION": {"OLLAMA_FLASH_ATTENTION", FlashAttention, "Enabled flash attention"},
"OLLAMA_HOST": {"OLLAMA_HOST", "", "IP Address for the ollama server (default 127.0.0.1:11434)"}, "OLLAMA_HOST": {"OLLAMA_HOST", "", "IP Address for the ollama server (default 127.0.0.1:11434)"},
"OLLAMA_KEEP_ALIVE": {"OLLAMA_KEEP_ALIVE", KeepAlive, "The duration that models stay loaded in memory (default \"5m\")"}, "OLLAMA_KEEP_ALIVE": {"OLLAMA_KEEP_ALIVE", KeepAlive, "The duration that models stay loaded in memory (default \"5m\")"},
"OLLAMA_LLM_LIBRARY": {"OLLAMA_ORIGINS", LLMLibrary, ""}, "OLLAMA_LLM_LIBRARY": {"OLLAMA_LLM_LIBRARY", LLMLibrary, "Set LLM library to bypass autodetection"},
"OLLAMA_MAX_LOADED_MODELS": {"OLLAMA_MAX_LOADED_MODELS", MaxRunners, "Maximum number of loaded models (default 1)"}, "OLLAMA_MAX_LOADED_MODELS": {"OLLAMA_MAX_LOADED_MODELS", MaxRunners, "Maximum number of loaded models (default 1)"},
"OLLAMA_MAX_QUEUE": {"OLLAMA_MAX_QUEUE", MaxQueuedRequests, "Maximum number of queued requests"}, "OLLAMA_MAX_QUEUE": {"OLLAMA_MAX_QUEUE", MaxQueuedRequests, "Maximum number of queued requests"},
"OLLAMA_MAX_VRAM": {"OLLAMA_MAX_VRAM", MaxVRAM, ""}, "OLLAMA_MAX_VRAM": {"OLLAMA_MAX_VRAM", MaxVRAM, "Maximum VRAM"},
"OLLAMA_MODELS": {"OLLAMA_MODELS", "", "The path to the models directory"}, "OLLAMA_MODELS": {"OLLAMA_MODELS", "", "The path to the models directory"},
"OLLAMA_NOHISTORY": {"OLLAMA_NOHISTORY", NoHistory, "Do not preserve readline history"}, "OLLAMA_NOHISTORY": {"OLLAMA_NOHISTORY", NoHistory, "Do not preserve readline history"},
"OLLAMA_NOPRUNE": {"OLLAMA_NOPRUNE", NoPrune, "Do not prune model blobs on startup"}, "OLLAMA_NOPRUNE": {"OLLAMA_NOPRUNE", NoPrune, "Do not prune model blobs on startup"},
"OLLAMA_NUM_PARALLEL": {"OLLAMA_NUM_PARALLEL", NumParallel, "Maximum number of parallel requests (default 1)"}, "OLLAMA_NUM_PARALLEL": {"OLLAMA_NUM_PARALLEL", NumParallel, "Maximum number of parallel requests (default 1)"},
"OLLAMA_ORIGINS": {"OLLAMA_ORIGINS", AllowOrigins, "A comma separated list of allowed origins"}, "OLLAMA_ORIGINS": {"OLLAMA_ORIGINS", AllowOrigins, "A comma separated list of allowed origins"},
"OLLAMA_RUNNERS_DIR": {"OLLAMA_RUNNERS_DIR", RunnersDir, ""}, "OLLAMA_RUNNERS_DIR": {"OLLAMA_RUNNERS_DIR", RunnersDir, "Location for runners"},
"OLLAMA_TMPDIR": {"OLLAMA_TMPDIR", TmpDir, "Location for temporary files"}, "OLLAMA_TMPDIR": {"OLLAMA_TMPDIR", TmpDir, "Location for temporary files"},
} }
} }