matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 07:46:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

llm: introduce k/v context quantization (vRAM improvements) (#6279)

Browse Source
This commit is contained in:
Sam
2024-12-04 10:57:19 +11:00
committed by GitHub
parent 2b82c5a8a1
commit 1bdab9fdb1
10 changed files with 147 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
envconfig/config.go
View File

@@ -153,6 +153,8 @@ var (
Debug = Bool("OLLAMA_DEBUG")
// FlashAttention enables the experimental flash attention feature.
FlashAttention = Bool("OLLAMA_FLASH_ATTENTION")
// KvCacheType is the quantization type for the K/V cache.
KvCacheType = String("OLLAMA_KV_CACHE_TYPE")
// NoHistory disables readline history.
NoHistory = Bool("OLLAMA_NOHISTORY")
// NoPrune disables pruning of model blobs on startup.
@@ -234,6 +236,7 @@ func AsMap() map[string]EnvVar {
ret := map[string]EnvVar{
"OLLAMA_DEBUG": {"OLLAMA_DEBUG", Debug(), "Show additional debug information (e.g. OLLAMA_DEBUG=1)"},
"OLLAMA_FLASH_ATTENTION": {"OLLAMA_FLASH_ATTENTION", FlashAttention(), "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\")"},