Josh Yan
163ee9a8b0
isLocal firstdraft
2024-07-22 15:51:52 -07:00
Josh Yan
de7b2f3948
clean
2024-07-22 15:51:52 -07:00
Josh Yan
f27c66fb0c
rm bench
2024-07-22 15:51:52 -07:00
Josh Yan
a238191798
rm config
2024-07-22 15:51:52 -07:00
Josh Yan
6436c7a375
rm config
2024-07-22 15:51:52 -07:00
Josh Yan
896a15874e
clean
2024-07-22 15:51:52 -07:00
Josh Yan
56008688a1
local path
2024-07-22 15:51:52 -07:00
Josh Yan
d14d38e940
still works
2024-07-22 15:51:52 -07:00
Josh Yan
03df02883d
rebase
2024-07-22 15:51:52 -07:00
Josh Yan
ae49abf80a
benchmark
2024-07-22 15:51:52 -07:00
Josh Yan
2c450502db
on disk copy
2024-07-22 15:51:52 -07:00
Josh Yan
46b76aeb46
start tests
2024-07-22 15:51:52 -07:00
Josh Yan
0e01da82d6
errorsis
2024-07-22 15:51:31 -07:00
Josh Yan
6b1b85ba3d
hide initialize keypair
2024-07-22 15:41:04 -07:00
Josh Yan
5603441538
test
2024-07-22 13:58:50 -07:00
Josh Yan
76b4dfcc9e
auth
2024-07-22 13:54:02 -07:00
Daniel Hiltgen
5784c05397
Merge pull request #5854 from dhiltgen/win_exit_status
...
Refine error reporting for subprocess crash
2024-07-22 10:40:22 -07:00
Daniel Hiltgen
f14aa5435d
Merge pull request #5855 from dhiltgen/remove_max_vram
...
Remove no longer supported max vram var
2024-07-22 10:35:29 -07:00
Jeffrey Morgan
f8fedbda20
Update llama.cpp submodule commit to d94c6e0c ( #5805 )
2024-07-22 12:42:00 -04:00
Jeffrey Morgan
b3e5491e41
server: collect nested tool call objects when parsing ( #5824 )
2024-07-22 12:38:03 -04:00
Daniel Hiltgen
cc269ba094
Remove no longer supported max vram var
...
The OLLAMA_MAX_VRAM env var was a temporary workaround for OOM
scenarios. With Concurrency this was no longer wired up, and the simplistic
value doesn't map to multi-GPU setups. Users can still set `num_gpu`
to limit memory usage to avoid OOM if we get our predictions wrong.
2024-07-22 09:08:11 -07:00
Daniel Hiltgen
a3c20e3f18
Refine error reporting for subprocess crash
...
On windows, the exit status winds up being the search term many
users search for and end up piling in on issues that are unrelated.
This refines the reporting so that if we have a more detailed message
we'll suppress the exit status portion of the message.
2024-07-22 08:52:16 -07:00
Jeffrey Morgan
80ee9b5e47
Remove out of space test temporarily ( #5825 )
2024-07-21 00:22:11 -04:00
Jeffrey Morgan
5534f2cc6a
llm: consider head_dim in llama arch ( #5817 )
2024-07-20 21:48:12 -04:00
Daniel Hiltgen
d321297d8a
Merge pull request #5815 from dhiltgen/win_rocm_gfx_features
...
Adjust windows ROCm discovery
2024-07-20 16:02:55 -07:00
Daniel Hiltgen
06e5d74e34
Merge pull request #5506 from dhiltgen/sched_tests
...
Refine scheduler unit tests for reliability
2024-07-20 15:48:39 -07:00
Daniel Hiltgen
5d707e6fd5
Merge pull request #5583 from dhiltgen/integration_improvements
...
Fix context exhaustion integration test for small gpus
2024-07-20 15:48:21 -07:00
Daniel Hiltgen
283948c83b
Adjust windows ROCm discovery
...
The v5 hip library returns unsupported GPUs which wont enumerate at
inference time in the runner so this makes sure we align discovery. The
gfx906 cards are no longer supported so we shouldn't compile with that
GPU type as it wont enumerate at runtime.
2024-07-20 15:17:50 -07:00
Jeffrey Morgan
1475eab95f
add patch for tekken ( #5807 )
2024-07-20 13:41:21 -04:00
Jeffrey Morgan
20090f3172
preserve last assistant message ( #5802 )
2024-07-19 20:19:26 -07:00
Jeffrey Morgan
69a2d4ccff
Fix generate test flakyness ( #5804 )
2024-07-19 19:11:25 -07:00
Josh
e8b954c646
server: validate template ( #5734 )
...
add template validation to modelfile
2024-07-19 15:24:29 -07:00
royjhan
c57317cbf0
OpenAI: Function Based Testing ( #5752 )
...
* distinguish error forwarding
* more coverage
* rm comment
2024-07-19 11:37:12 -07:00
royjhan
51b2fd299c
adjust openai chat msg processing ( #5729 )
2024-07-19 11:19:20 -07:00
Michael Yang
d0634b1596
Merge pull request #5780 from ollama/mxyng/tools
...
fix parsing tool calls: break on unexpected eofs
2024-07-18 12:14:10 -07:00
Michael Yang
43606d6d6a
fix parsing tool calls
2024-07-18 12:08:11 -07:00
Jeffrey Morgan
70b1010fa5
server: check for empty tools array too ( #5779 )
2024-07-18 11:44:57 -07:00
Jeffrey Morgan
84e5721f3a
always provide content even if empty ( #5778 )
2024-07-18 11:28:19 -07:00
Jeffrey Morgan
319fb1ce03
server: only parse tool calls if tools are provided ( #5771 )
...
* server: only parse tool calls if tools are provided
* still set `resp.Message.Content`
2024-07-18 08:50:23 -07:00
Michael Yang
b255445557
marshal json automatically for some template values ( #5758 )
2024-07-17 15:35:11 -07:00
Michael Yang
b23424bb3c
Merge pull request #5753 from ollama/mxyng/parse-tool-call
...
parse tool call as individual objects
2024-07-17 11:47:53 -07:00
Michael Yang
5fd6988126
parse tool call as individual objects
2024-07-17 11:19:04 -07:00
Michael Yang
5b82960df8
stub response ( #5750 )
2024-07-17 10:39:22 -07:00
Michael Yang
cc9a252d8c
Merge pull request #5732 from ollama/mxyng/cleanup
...
remove ToolCall from GenerateResponse
2024-07-17 10:26:54 -07:00
Pákozdi György
d281a6e603
add sidellama link ( #5702 )
2024-07-17 10:24:44 -07:00
royjhan
154f6f45d4
OpenAI: Support Tools ( #5614 )
...
* reopen pr
* tools
* remove tc from stream for now
* ID and Function
* openai expects arguments to be a string (#5739 )
* mutually exclusive content and tool calls
* clean up
---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com >
2024-07-16 20:52:59 -07:00
royjhan
0d41623b52
OpenAI: Add Suffix to v1/completions ( #5611 )
...
* add suffix
* remove todo
* remove TODO
* add to test
* rm outdated prompt tokens info md
* fix test
* fix test
2024-07-16 20:50:14 -07:00
Michael Yang
c279f96371
remove ToolCall from GenerateResponse
2024-07-16 15:22:49 -07:00
Michael Yang
499e87c9ba
Merge pull request #5730 from ollama/mxyng/cleanup
...
remove unneeded tool calls
2024-07-16 14:42:13 -07:00
Michael Yang
cd0853f2d5
Merge pull request #5207 from ollama/mxyng/suffix
...
add insert support to generate endpoint
2024-07-16 14:37:32 -07:00
