When numPredict is set, the user will receive one less token
than the requested limit. In addition, the stats will incorrectly
show the number of tokens returned as the limit. In cases where
numPredict is not set, the number of tokens is reported correctly.
This occurs because numPredict is checked when setting up the next
batch but hitting the limit will terminate the current batch as well.
Instead, is is better to check the limit as we actually predict them.
When trying to use cloud model with OLLAMA_HOST="ollama.com" while not signed in a helpful error message is displayed when the user is not signed in telling them they must sign in to use cloud models. This should be the same experience for models which specify a remote instance.
If a sequence is replaced in s.seqs while a batch is computing, the old logits can be decoded into the new sequence. This change rechecks the sequence pointer after compute and skips decoding for replaced entries, preventing stale results from being applied.
Change the truncation algorithm to start with all messages and remove
from the front until it fits, rather than adding messages one at a time
from the back. This reduces tokenization calls from O(n) to O(1) in the
common case where all messages fit in context.
When a browser is available open it to the connect URL automatically when running the `ollama signin` command. Browser is not opened in any other unauthorized scenario.
When context length is clamped to the model's trained context length,
ollama ps now shows the actual clamped value instead of the originally
configured value.
When launching OpenClaw without prior onboarding, run the onboarding
wizard instead of going straight to gateway. This ensures proper
gateway configuration (mode, token, etc.) before first use.
- Add onboarded() to check for wizard.lastRunAt marker in config
- Run onboard with --auth-choice skip --gateway-token ollama for fresh installs
- Existing installs (onboarding completed) run gateway directly
Fix typo in three error messages where 'baackend' was written instead
of 'backend' in the /health endpoint handler when initializing the
dummy model load.
* parsers/ministral: fix nested tool call parsing by counting brace nesting
* fix lint error
* parsers: refactor ministral parser
The old one was very tied to expecting to see only one token at a time,
which I don't like to assume (who knows what the future might hold wrt
speculative decoding, etc). This new one follows a similar structure to
qwen3-coder's parser, which incidentally makes it easier to test as well
(since we can test the individual events that come out when given
particular inputs).
---------
Co-authored-by: Devon Rifkin <drifkin@drifkin.net>
Use the original key dimension (qkNopeHeadDim + qkRopeHeadDim = 256) for
the attention scale instead of the MLA absorbed dimension (kvLoraRank +
qkRopeHeadDim = 576).
MLA absorption is a mathematically equivalent reorganization of the
attention computation - it should not change the effective attention
scale. The scale should match training, which uses 1/sqrt(256).
This improves tool calling and model looping issues.
CGO_CFLAGS and CGO_CXXFLAGS were being set without optimization flags,
which overrides Go's default -O2 and results in unoptimized C++ code.
This caused significant performance degradation in release builds
compared to local `go build` which uses the default optimization.
- build_darwin.sh: add -O3 to CGO_CFLAGS and CGO_CXXFLAGS exports
- Dockerfile: preserve CGO_CFLAGS/CGO_CXXFLAGS from build args instead
of overwriting them
- app/README.md: update documentation to include -O3
* update README ruby link
the ollama-ai ruby gem is vastly less popular and seems unmaintained
https://rubygems.org/gems/ollama-ai
the defacto standard with the most downloads in the ruby ecosystem is ruby_llm
https://rubygems.org/gems/ruby_llm
I would link to that to avoid complication and guarantee feature compatibility with ollama.
* Update gem link ruby_llm from website to GitHub
ollama links mostly to github, not project websites, hence link to ruby_llm github.
Use nthreads=128 for ncols=4 configurations in flash attention tile
kernel to reduce shared memory usage below 48KB limit on Maxwell
architectures (sm_50/52).
With nthreads=256 and ncols=4, np=2 which caused shared memory to
exceed 48KB. With nthreads=128 and ncols=4, np=1 keeps shared memory
under the limit.
The nvidia_fp32 config for (576, 512) head sizes had nbatch_fa=32,
which caused zero-sized arrays when computing array dimensions:
nbatch_fa / (np * warp_size) = 32 / (2 * 32) = 0
This resulted in CUDA compilation failures on CUDA 12 (Windows and
Linux arm64):
- "static assertion failed with nbatch_fa % (np*warp_size) != 0"
- "the size of an array must be greater than zero"
Fix by changing nbatch_fa from 32 to 64 for all (576, 512) configs
in the nvidia_fp32 function, matching the nvidia_fp16 and AMD configs.
