third-party-mirrors/ollama
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,370 Commits 177 Branches 161 Tags
Commit Graph

2370 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Blake Mizerany
c95f97689b utils/upload: init 2024-04-02 14:15:21 -07:00
Blake Mizerany
618eb5b909 registry: multipart push 2024-04-02 13:40:23 -07:00
Daniel Hiltgen
841adda157 Fix windows lint CI flakiness 2024-04-02 12:22:16 -07:00
Daniel Hiltgen
0035e31af8 Bump to b2581 2024-04-02 11:53:07 -07:00
Blake Mizerany
eb75418be9 build/blob: test ParseRef round-trip 2024-04-02 11:45:01 -07:00
Blake Mizerany
9959da05de build/blob: break out test refs for other tests/fuzzing 2024-04-02 11:38:10 -07:00
Daniel Hiltgen
c863c6a96d
Merge pull request #3218 from dhiltgen/subprocess 
Switch back to subprocessing for llama.cpp
 2024-04-02 10:49:44 -07:00
Blake Mizerany
aff7970628 build: remove superfluous parseCompleteRef 2024-04-01 23:41:42 -07:00
Blake Mizerany
628f1feb36 build: back to taking manifests as []byte 
Its nicer to have the manifests be an opaque []byte, rather than a
struct. This way users of the build package don't need to know about the
internal structure of the manifests. The registry can interpret the
manifests as it sees fit, while letting build keep its own Go type of
manifest which is easier to work with in the build package.
 2024-04-01 23:18:58 -07:00
Blake Mizerany
ce3125afd5 registry: add New and take a minio client as argument 2024-04-01 22:53:49 -07:00
Blake Mizerany
f488652ba7 build: make Build accept only refs without builds 2024-04-01 22:12:43 -07:00
Blake Mizerany
2318ed2919 build: remove unused manifest() 2024-04-01 21:59:38 -07:00
Blake Mizerany
b1b8be33d9 build: cleanup error names and other things 2024-04-01 21:57:34 -07:00
Blake Mizerany
876f7eab81 build: move Manifest from internal/blobstore to build 
It was getting confusing to have the arbirary handling of manifests in
the blobstore. It also prevented us from using model.Ref in the
blobstore because of cyclic dependencies.

This is much easier to grok now.
 2024-04-01 21:43:30 -07:00
Blake Mizerany
7cfc8a0838 build/blob: fix awkward Ref type 2024-04-01 21:25:18 -07:00
Daniel Hiltgen
1f11b52511 Refined min memory from testing 2024-04-01 16:48:33 -07:00
Daniel Hiltgen
526d4eb204 Release gpu discovery library after use 
Leaving the cudart library loaded kept ~30m of memory
pinned in the GPU in the main process.  This change ensures
we don't hold GPU resources when idle.
 2024-04-01 16:48:33 -07:00
Daniel Hiltgen
0a74cb31d5 Safeguard for noexec 
We may have users that run into problems with our current
payload model, so this gives us an escape valve.
 2024-04-01 16:48:33 -07:00
Daniel Hiltgen
10ed1b6292 Detect too-old cuda driver 
"cudart init failure: 35" isn't particularly helpful in the logs.
 2024-04-01 16:48:33 -07:00
Daniel Hiltgen
4fec5816d6 Integration test improvements 
Cleaner shutdown logic, a bit of response hardening
 2024-04-01 16:48:18 -07:00
Daniel Hiltgen
0a0e9f3e0f Apply 01-cache.diff 2024-04-01 16:48:18 -07:00
Daniel Hiltgen
58d95cc9bd Switch back to subprocessing for llama.cpp 
This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems.  This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.
 2024-04-01 16:48:18 -07:00
Patrick Devine
3b6a9154dd
Simplify model conversion (#3422) 2024-04-01 16:14:53 -07:00
Michael Yang
d6dd2ff839
Merge pull request #3241 from ollama/mxyng/mem 
update memory estimations for gpu offloading
 2024-04-01 13:59:14 -07:00
Michael Yang
e57a6ba89f
Merge pull request #2926 from ollama/mxyng/decode-ggml-v2 
refactor model parsing
 2024-04-01 13:58:13 -07:00
Michael Yang
12ec2346ef
Merge pull request #3442 from ollama/mxyng/generate-output 
fix generate output
 2024-04-01 13:56:09 -07:00
Michael Yang
1ec0df1069 fix generate output 2024-04-01 13:47:34 -07:00
Michael Yang
91b3e4d282 update memory calcualtions 
count each layer independently when deciding gpu offloading
 2024-04-01 13:16:32 -07:00
Michael Yang
d338d70492 refactor model parsing 2024-04-01 13:16:15 -07:00
Philipp Gillé
011bb67351
Add chromem-go to community integrations (#3437) 2024-04-01 11:17:37 -04:00
Saifeddine ALOUI
d124627202
Update README.md (#3436) 2024-04-01 11:16:31 -04:00
Jesse Zhang
b0a8246a69
Community Integration: CRAG Ollama Chat (#3423) 
Corrective Retrieval Augmented Generation Demo, powered by Langgraph and Streamlit 🤗

Support: 
- Ollama
- OpenAI APIs
 2024-04-01 11:16:14 -04:00
Blake Mizerany
fd411b3cf6 registry: commit Manifest 2024-03-31 18:20:19 -07:00
Blake Mizerany
04f38cf3f4 registry: commit manifest on successful /v1/push 2024-03-31 15:09:24 -07:00
Blake Mizerany
c0eddb10fd registry: use exact match on path 2024-03-31 15:01:26 -07:00
Blake Mizerany
60ef0e6b4a oweb: remove Fault 
Also, fix typo in the comment.
 2024-03-31 15:00:25 -07:00
Blake Mizerany
48c60c01e2 registry: move req/resp types to registry/apitype 2024-03-31 12:23:10 -07:00
Blake Mizerany
eb2c442a01 oweb: make DecodeUserJSON take a field name 
This allows for better error messages when decoding fails. For example,
instead of:

    {"code":"invalid_json","message":"unexpected end of JSON input"}

We now get:

    {"code":"invalid_json","field":"manifest","message":"unexpected end of JSON input"}
 2024-03-31 11:36:51 -07:00
Blake Mizerany
c87fe7df48 client/ollama: make Error.Message optional 2024-03-31 11:12:50 -07:00
Blake Mizerany
5182a1dfb1 client/ollama: document Do 2024-03-31 11:04:20 -07:00
Blake Mizerany
a32e7857b2 client/ollama: docs for Error type 2024-03-31 11:00:07 -07:00
Blake Mizerany
6acc205de0 client/ollama: install and use (*Client).HTTPClient 2024-03-31 10:54:17 -07:00
Blake Mizerany
f6e02d4bc7 client/ollama: Do take a *Client 2024-03-31 10:52:56 -07:00
Yaroslav
e6fb39c182
Update README.md (#3378) 
Plugins list updated
 2024-03-31 13:10:05 -04:00
Blake Mizerany
e1d457c73e client/ollama: report invalid server error response with raw bytes 2024-03-31 09:43:03 -07:00
Blake Mizerany
cd5df121a5 client: include Status in json Error response for symmetry. 
Also, remove RawBody from error, which was previously used for
debugging.
 2024-03-31 09:30:01 -07:00
Blake Mizerany
112ffed189 oweb: move Error and Do to client/ollama 
This allows users of the ollama client library to need only import the
client/ollama package, rather than the oweb package as well when
inspecting errors.
 2024-03-31 09:25:07 -07:00
Blake Mizerany
c49947dcf5 init 2024-03-31 09:24:53 -07:00
sugarforever
e1f1c374ea
Community Integration: ChatOllama (#3400) 
* Community Integration: ChatOllama

* fixed typo
 2024-03-30 22:46:50 -04:00
Jeffrey Morgan
06a1508bfe
Update 90_bug_report.yml 2024-03-29 10:11:17 -04:00