Mirror_Repos/ollama_ollama
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add ability to turn on debug request logging (#14106)

Browse Source 
If `OLLAMA_DEBUG_LOG_REQUESTS` is set, then on server startup a temp
folder will be created. Upon any inference request, the body will be
logged to a file in this folder, as well as a small shell script to
"replay" the request using cURL.

This is just intended for debugging scenarios, not as something to turn
on normally.
This commit is contained in:
Devon Rifkin
2026-03-19 17:08:17 -07:00
committed by GitHub
parent 126d8db7f3
commit 46cb7795e1
4 changed files with 307 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
envconfig/config.go
+25 -22
View File
@@ -214,6 +214,8 @@ func LogLevel() slog.Level {
var (
// FlashAttention enables the experimental flash attention feature.
FlashAttention = BoolWithDefault("OLLAMA_FLASH_ATTENTION")
// DebugLogRequests logs inference requests to disk for replay/debugging.
DebugLogRequests = Bool("OLLAMA_DEBUG_LOG_REQUESTS")
// KvCacheType is the quantization type for the K/V cache.
KvCacheType = String("OLLAMA_KV_CACHE_TYPE")
// NoHistory disables readline history.
@@ -302,28 +304,29 @@ type EnvVar struct {
func AsMap() map[string]EnvVar {
ret := map[string]EnvVar{
"OLLAMA_DEBUG": {"OLLAMA_DEBUG", LogLevel(), "Show additional debug information (e.g. OLLAMA_DEBUG=1)"},
"OLLAMA_FLASH_ATTENTION": {"OLLAMA_FLASH_ATTENTION", FlashAttention(false), "Enabled flash attention"},
"OLLAMA_KV_CACHE_TYPE": {"OLLAMA_KV_CACHE_TYPE", KvCacheType(), "Quantization type for the K/V cache (default: f16)"},
"OLLAMA_GPU_OVERHEAD": {"OLLAMA_GPU_OVERHEAD", GpuOverhead(), "Reserve a portion of VRAM per GPU (bytes)"},
"OLLAMA_HOST": {"OLLAMA_HOST", 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_LLM_LIBRARY": {"OLLAMA_LLM_LIBRARY", LLMLibrary(), "Set LLM library to bypass autodetection"},
"OLLAMA_LOAD_TIMEOUT": {"OLLAMA_LOAD_TIMEOUT", LoadTimeout(), "How long to allow model loads to stall before giving up (default \"5m\")"},
"OLLAMA_MAX_LOADED_MODELS": {"OLLAMA_MAX_LOADED_MODELS", MaxRunners(), "Maximum number of loaded models per GPU"},
"OLLAMA_MAX_QUEUE": {"OLLAMA_MAX_QUEUE", MaxQueue(), "Maximum number of queued requests"},
"OLLAMA_MODELS": {"OLLAMA_MODELS", Models(), "The path to the models directory"},
"OLLAMA_NO_CLOUD": {"OLLAMA_NO_CLOUD", NoCloud(), "Disable Ollama cloud features (remote inference and web search)"},
"OLLAMA_NOHISTORY": {"OLLAMA_NOHISTORY", NoHistory(), "Do not preserve readline history"},
"OLLAMA_NOPRUNE": {"OLLAMA_NOPRUNE", NoPrune(), "Do not prune model blobs on startup"},
"OLLAMA_NUM_PARALLEL": {"OLLAMA_NUM_PARALLEL", NumParallel(), "Maximum number of parallel requests"},
"OLLAMA_ORIGINS": {"OLLAMA_ORIGINS", AllowedOrigins(), "A comma separated list of allowed origins"},
"OLLAMA_SCHED_SPREAD": {"OLLAMA_SCHED_SPREAD", SchedSpread(), "Always schedule model across all GPUs"},
"OLLAMA_MULTIUSER_CACHE": {"OLLAMA_MULTIUSER_CACHE", MultiUserCache(), "Optimize prompt caching for multi-user scenarios"},
"OLLAMA_CONTEXT_LENGTH": {"OLLAMA_CONTEXT_LENGTH", ContextLength(), "Context length to use unless otherwise specified (default: 4k/32k/256k based on VRAM)"},
"OLLAMA_EDITOR": {"OLLAMA_EDITOR", Editor(), "Path to editor for interactive prompt editing (Ctrl+G)"},
"OLLAMA_NEW_ENGINE": {"OLLAMA_NEW_ENGINE", NewEngine(), "Enable the new Ollama engine"},
"OLLAMA_REMOTES": {"OLLAMA_REMOTES", Remotes(), "Allowed hosts for remote models (default \"ollama.com\")"},
"OLLAMA_DEBUG": {"OLLAMA_DEBUG", LogLevel(), "Show additional debug information (e.g. OLLAMA_DEBUG=1)"},
"OLLAMA_DEBUG_LOG_REQUESTS": {"OLLAMA_DEBUG_LOG_REQUESTS", DebugLogRequests(), "Log inference request bodies and replay curl commands to a temp directory"},
"OLLAMA_FLASH_ATTENTION": {"OLLAMA_FLASH_ATTENTION", FlashAttention(false), "Enabled flash attention"},
"OLLAMA_KV_CACHE_TYPE": {"OLLAMA_KV_CACHE_TYPE", KvCacheType(), "Quantization type for the K/V cache (default: f16)"},
"OLLAMA_GPU_OVERHEAD": {"OLLAMA_GPU_OVERHEAD", GpuOverhead(), "Reserve a portion of VRAM per GPU (bytes)"},
"OLLAMA_HOST": {"OLLAMA_HOST", 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_LLM_LIBRARY": {"OLLAMA_LLM_LIBRARY", LLMLibrary(), "Set LLM library to bypass autodetection"},
"OLLAMA_LOAD_TIMEOUT": {"OLLAMA_LOAD_TIMEOUT", LoadTimeout(), "How long to allow model loads to stall before giving up (default \"5m\")"},
"OLLAMA_MAX_LOADED_MODELS": {"OLLAMA_MAX_LOADED_MODELS", MaxRunners(), "Maximum number of loaded models per GPU"},
"OLLAMA_MAX_QUEUE": {"OLLAMA_MAX_QUEUE", MaxQueue(), "Maximum number of queued requests"},
"OLLAMA_MODELS": {"OLLAMA_MODELS", Models(), "The path to the models directory"},
"OLLAMA_NO_CLOUD": {"OLLAMA_NO_CLOUD", NoCloud(), "Disable Ollama cloud features (remote inference and web search)"},
"OLLAMA_NOHISTORY": {"OLLAMA_NOHISTORY", NoHistory(), "Do not preserve readline history"},
"OLLAMA_NOPRUNE": {"OLLAMA_NOPRUNE", NoPrune(), "Do not prune model blobs on startup"},
"OLLAMA_NUM_PARALLEL": {"OLLAMA_NUM_PARALLEL", NumParallel(), "Maximum number of parallel requests"},
"OLLAMA_ORIGINS": {"OLLAMA_ORIGINS", AllowedOrigins(), "A comma separated list of allowed origins"},
"OLLAMA_SCHED_SPREAD": {"OLLAMA_SCHED_SPREAD", SchedSpread(), "Always schedule model across all GPUs"},
"OLLAMA_MULTIUSER_CACHE": {"OLLAMA_MULTIUSER_CACHE", MultiUserCache(), "Optimize prompt caching for multi-user scenarios"},
"OLLAMA_CONTEXT_LENGTH": {"OLLAMA_CONTEXT_LENGTH", ContextLength(), "Context length to use unless otherwise specified (default: 4k/32k/256k based on VRAM)"},
"OLLAMA_EDITOR": {"OLLAMA_EDITOR", Editor(), "Path to editor for interactive prompt editing (Ctrl+G)"},
"OLLAMA_NEW_ENGINE": {"OLLAMA_NEW_ENGINE", NewEngine(), "Enable the new Ollama engine"},
"OLLAMA_REMOTES": {"OLLAMA_REMOTES", Remotes(), "Allowed hosts for remote models (default \"ollama.com\")"},
// Informational
"HTTP_PROXY": {"HTTP_PROXY", String("HTTP_PROXY")(), "HTTP proxy"},