* gmp-oss: common
* gpt-oss: attnetion sinks, swiglu_oai
* gpt-oss: WIP llama
Model loads and runs (CPU only), but PPL is much to high
(~1500 for 1st batch vs ~200 in mainline).
Is it because of SWA, because of vocab, or did I introduce a bug somewhere?
* gpt-oss: CPU seems to be working
It was the SWA thta was missing in the previous commit.
There are issues with EOG tokens, so this still needs to be added.
* CUDA: ADD_ID
Just a copy from mainline
* gpt-oss: Seems to be working on CUDA
* gpt-oss: add sinks to the attn-vec kernels
* CUDA: add head size of 64 to new mma
Haven't turned it on yet, but observe slightly better PP and slightly
worse TG performance with that.
* gpt-oss: add ability to use -fmoe (only CUDA for now)
* Move row sums to the write place
* Add sinks to iqk flash attention
* gpt_oss: Implement -fmoe on the CPU
* Simdify swiglu_oai
Turning it off for now as performance becomes more variable,
so perhaps I'm running into thermal trottling imore often
because of making the CPU work too hard.
* llama: factor out model loader
* Builds successfully
* It runs, but mmap does not work
* Fix llama_mmap so mmap works
* Minor
* Fix CUDA after latest changes
* Attempt to use CUDA graphs with MoE models - not working
* CUDA graphs WIP - still not working
* CUDA graphs - seems to be working
Likely not all MLA variants are working.
I no longer remember why I added the q8_0 cpy that
transposes the tensor, but if really needed, this is now
missing. Also missing is q6_0.
* Make q8_0 cache work for DeepSeek models with CUDA graphs
* cuda: cpy for q6_0
* Fix llama_mmap on non-Linux platforms
* Adding forgotten file
* Iterating on Windows build failures
* cuda: re-add q8_0 -> q8_0 transpose
so mla = 2 can be used with CUDA graphs and q8_0 cache.
* Disable graphs without -fmoe
* Minor
* Turn graphs on by default
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* mxfp4: basics
* mxfp4: Zen4 GEMM
* mxfp4: repacked GEMM (AVX2/Zen4)
* mxfp4: AVX2 GEMM
* mxfp4: NEON GEMM
* mxfp4: repacked GEMM (NEON)
* mxfp4: Metal
* Fix quantized K cache without FA (#680)
* Prevent assert with quantized K cache and no FA
* Fix MMQ when running with quantized K cache without FA
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Fix for Deepseek r1 parsing (#676)
* Implement function calling / tools for ik_llama.cpp for Kimi K2
* Implement basic tool choice
* Backport llama.cpp tool calls support
* Enhance function calls with improved chat parser and string utilities
- Add new chat.h/chat.cpp and chat-parser.h/chat-parser.cpp for better chat handling
- Improve function calls parsing with fallback to llama.cpp builder pattern
- Add string utility functions (starts_with, ends_with, find_partial_stop)
- Update README with function calls testing instructions
- Enhance Kimi K2 parser and function calls documentation
- Add comprehensive test suite for function calls
- Update CMakeLists.txt and Makefile for new components
* Enhance function calling with unified streaming and parser improvements
- Fix streaming content cleanup to prevent function syntax in output
- Unify content extraction patterns with llama.cpp approach
- Improve Kimi K2 parser robustness and partial content handling
- Add comprehensive test coverage for function call scenarios
- Optimize chat message parsing and diff computation
* Replace hardcoded values in kimi_k2_parser.hpp with named constants
- Add compile-time constants for all token format markers
- Add compile-time constants for XML format markers
- Add compile-time constants for simple format patterns
- Replace all hardcoded string literals with named constants
- Use compile-time length calculation to avoid manual counting
- Improve maintainability and reduce magic numbers throughout parser
* Fix duplicate common_chat_parse definition
- Remove duplicate implementation from chat-parser.cpp
- Keep single implementation in chat.cpp following llama.cpp patterns
- Resolves linker error: multiple definition of common_chat_parse
* Fix JSON assertion failure in function call parsing
- Add proper validation that 'function' field is an object before accessing nested keys
- Handle missing 'arguments' field gracefully with default "{}"
- Prevents crash when parsing malformed tool call JSON structures
* Add comprehensive Qwen3 XML tool calling support with unit tests
- Implement Qwen3 XML parser with <tool_call>{"name": "func", "arguments": {...}}</tool_call> format
- Add model detection and routing for Qwen3 vs Kimi-K2 formats
- Create 8 comprehensive unit tests covering parsing, streaming, error handling
- Fix token format cleaning bug in kimi_k2_parser.hpp processing order
- Remove progressive parsing code and related utilities
- Add tool injection support for Qwen3 format in server utils
* Add DeepSeek R1 function calling support with comprehensive unit tests
- Implement complete DeepSeek R1 tool call parsing in common_chat_parser.cpp
- Add DeepSeek R1 model detection and tool injection in deepseek_r1_tools.hpp
- Update function_calls.hpp with DeepSeek R1 integration and content extraction
- Update documentation to reflect support for Kimi-K2, Qwen3, and DeepSeek R1 models
- Add comprehensive unit tests for DeepSeek R1 reasoning, tool calls, and integration
- Port exact implementation patterns from original llama.cpp for compatibility
Key features:
- Native DeepSeek R1 format: <｜tool▁calls▁begin｜>function<｜tool▁sep｜>name```json{}```<｜tool▁call▁end｜><｜tool▁calls▁end｜>
- Reasoning content extraction from <think>...</think> tags
- Multiple tool calls support with separate call blocks
- Model detection for deepseek-r1, deepseek_r1 naming patterns
- Integration with incremental parsing and streaming support
* Add partial parsing support for JSON and regex
- json-partial.h/cpp: JSON partial parsing functionality
- regex-partial.h/cpp: Regex partial parsing functionality
* Add format_chat integration tests for Qwen3 tool injection
- Add test_qwen3_format_chat_integration() to validate tool injection pipeline
- Test tool injection conditions and system message enhancement
- Verify JSON formatting and anti-preamble instructions
- Add comprehensive test documentation
Tests confirm tool injection works correctly - conversational preamble
issue is not in ik_llama.cpp but likely in UI configuration.
* Fix Qwen3 tool call parsing - pass model name to parser
Server was not passing model name to parse_chat_message_incremental(),
causing Qwen3 to fall back to Kimi-K2 parser and return tool calls
as content instead of proper tool_calls array.
* Fix non-streaming path to use model-specific parsing
Non-streaming responses were hardcoded to use Kimi-K2 format,
causing Qwen3 XML tool calls to be returned as content instead
of proper tool_calls array. Now uses same model detection as
streaming path for consistency.
* Update Qwen3 function call handling in server and tests
- Enhanced server function call detection and response formatting
- Improved test coverage for Qwen3 tool call scenarios
- Refined XML parsing for better tool execution support
* Add DeepSeek-R1 function call parsing support
Implements comprehensive parsing for all 4 DeepSeek-R1 function call formats:
- Format 1: Standard function call syntax (already supported)
- Format 2: Alternative function call patterns (already supported)
- Format 3: Tools array format - function\n```json\n{"tools": [...]}
- Format 4: XML wrapped format - <tool_call>function</think>Name\n```json\n{...}```</tool_call>
Key changes:
- Added parse_deepseek_r1_tools_array() following original parse_prefixed_json_tool_call_array pattern
- Added parse_deepseek_r1_xml_wrapped() following Hermes-2-Pro XML wrapper patterns
- Integrated both parsers into exception handling chain for robust fallback
- Added comprehensive TDD test coverage for all formats
- Anonymized all confidential information while preserving functionality
Resolves tool_calls_count=0 issue where DeepSeek-R1 models generated valid tool calls
but server failed to parse them correctly.
* Update function_calls.md documentation for DeepSeek-R1 Format 4
- Added Format 4 (XML wrapped) documentation with examples
- Updated implementation notes with correct parser order (3→4→1→2)
- Marked all DeepSeek-R1 formats as working (July 2025 update)
- Updated test status for Format 3 and 4 as passing
- Added parse_deepseek_r1_xml_wrapped() function reference
- Corrected implementation file line numbers
* Fix merge conflict in test-function-calls.cpp
- Removed incomplete merge conflict marker from line 3027
- Ensured all tests compile and pass successfully
- All DeepSeek-R1 formats (1-4) working correctly
- All streaming and content cleaning tests passing
* Fix DeepSeek R1 parsing issue with responses wrapped in think tags
Restore missing consume_rest() call from working PR #648 implementation.
When responses don't contain tool calls, remaining content after reasoning
parsing must be preserved as displayable content.
Fixes issue where entire responses wrapped in <think> tags resulted in
empty content output.
* Implement proper reasoning handling following original llama.cpp patterns
- Add missing reasoning_format and reasoning_in_content fields to common_chat_syntax
- Update try_parse_reasoning to match original llama.cpp logic exactly
- Add TDD test case with reasoning_in_content=true for DeepSeek R1
- Following TDD: test should now pass with proper syntax configuration
Based on original llama.cpp implementation patterns.
* TDD SUCCESS: Fix DeepSeek R1 thinking tag termination issue
✅ Test passes with reasoning_in_content=true configuration
- Content properly preserved: '<think>content</think>' displays fully
- Reasoning field empty as expected
- Following TDD: test-first approach validates the fix
Next: Update server to automatically apply this configuration.
* Complete server integration fix for DeepSeek R1 thinking tag termination
- Server now automatically sets reasoning_in_content=true for DeepSeek R1 models
- Fixes issue where responses wrapped in <think> tags appear empty to users
* Add TDD test case for DeepSeek R1 thinking tag termination issue
- Test reproduces the exact failure scenario reported by user
- Validates that reasoning_in_content=true fixes the issue
- Demonstrates empty content problem and working solution
* Add remaining TDD test changes for DeepSeek R1 thinking tag fix
* Add debug output after upstream merge
* Remove temporary benchmark and debug files
- Remove tests/benchmark-progressive-parsing.cpp (development tool, not part of core functionality)
- Remove tests/reproduce_bug.sh (debugging script, not needed for PR)
* Port cpu moe options from mainline (#672)
* Port cpu moe options from mainline
* Use strdup and int32_t to follow coding guidelines
* maxfp4: CUDA dequantize
* mxfp4: CUDA GEMV
* mxfp4: CUDA MMQ
* mxfp4: minor CUDA tweaks
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Anton Sokolchenko <wsevendays@gmail.com>
Co-authored-by: Parsa <61601745+TheLegendOfKitty@users.noreply.github.com>
* iq1_kt: basics
* iq1_kt: CUDA dequantize
Testing with LlaMA-3.1-8B-Instruct, we get almost the same PPL
as iq2_xxs, so about 0.2 bpw fewer bits for the same quality.
* iq1_kt: CUDA MMQ
* iq1_kt: CUDA MMVQ
* iq1_kt: AVX2 GEMM/GEMV
* iq1_kt: convert/repack to q8_0_r8 (AVX2)
* iq1_kt: slightly faster GEMV
18.6 t/s -> 19.4 t/s
* iq1_kt: NEON GEMM/GEMV
Pathetic as usual
* iq1_kt: slightly faster NEON - still pathetic
* iq1_kt: tiny bit better GEMV on NEON
* iq1_kt: convert/repack to q8_0_r8 (NEON)
* iq1_kt: very slightly faster convert/repack to q8_0_r8 on NEON
* Adding frgotten file
* iq1_kt: add to constants.py
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Experiments for 2.6875 bpw quants
At least according to rmse, this is significantly better than
q2_K, while using only 1/16 more bits per weight.
* iq2_kl: basics
* iq2_kl: CUDA dequantize
* iq2_kl: small improvement in PPL
Also check the two neighbouring values for the block scale
and use the one that minimizes RMSE.
* iq2_kl: MMQ
Quite good: PP-512(L3-8B) = 8472 t/s.
* iq2_kl: MMVQ
We get PP-128(L3-8B) = 162 t/s.
Which means that this is not quite as good as it should be as
(almost) same bpq q2_K is at 170 t/s.
* iq2_kl: Zen4 GEMM/GEMV
Not particularly fast. I may need to think about rearranging the bits.
* iq2_kl: better Zen4
* iq2_kl: convert/repack to q8_k_r8 (AVX2)
* iq2_kl: AVX2 GEMM/GEMV
* iq2_kl: WIP NEON
The compiler started crashing!!!
* iq2_kl: NEON
Had to work around a compiler crash when using vzip2q_u8 using
vqtbl2q_u8.
* iq2_kl: convert/repack to q8_k_r8 (NEON)
* iq2_kl: Metal dequantize
* iq2_kl: Metal GEMV - pretty slow
* iq2_kl: Metal GEMV - slightly better (40 t/s -> 44.5 t/s)
* iq2_kl: Metal GEMV - slightly better (44.5 t/s -> 46.5 t/s)
* iq2_kl: Metal GEMV - slightly better (46.5 t/s -> 47.2 t/s)
* iq2_kl: slightly better Metal dequantize
PP-512 goes to 476 t/s up from 466 t/s.
* iq2_kl: slightly better Metal dequantize
PP-512 goes to 492 t/s up from 476 t/s.
* Add iq2_kl to constants.py
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* New iq4_kt trellis
The new trellis generates int8_t values via
sum_as_uint8_t[(ka * idx + kb) & 0x3f33f3f3f] - 126.
CUDA dequantize works.
AVX2 case Ny > 32 works, and we get 273 t/s for L3-8B.
PPL is on par or even slightly lower than original QTIP trellis.
* Something is not working with the AVX2 dot product
* New iq4_kt: CUDA MMVQ
* New iq4_kt: CUDA MMQ
* For now have only iq4_kt use the new trellis
* Fix iq2_kt that got broken along the way
* New iq4_kt: AVX2 dot product finally works
We get 13.6 t/s vs 8.4 t/s with the f16 trellis and f32 arithmetic.
Still somewhat slower than other quants, but no longer pathetic.
* New iq4_kt: fix vanilla AVX2
* New iq4_kt: NEON implementation
We get very respectable PP-512 = 120 t/s.
TG-128 is pathetic at 5.3 t/s, so 20+% slower than the f16 variant.
* New iq4_kt: slightly faster NEON
* New iq4_kt: slightly faster NEON
* New iq4_kt: faster NEON
We are now at 9.4 t/s, up from 6.6 t/s for the f16 trellis.
* Minor
* New iq4_kt trellis: not working Metal implementation
* Remove the extra 4 bytes of row meta data that is no longer used
* Cleanup
* Adding forgottent file
* Switching iq2_kt to new trellis - CUDA MMQ
* New iq2_kt: CUDA GEMV
* New iq2_kt: AVX2 dequantize
* New iq2_kt: AVX2 GEMM/GEMV
* Adding forgotten file
* New iq2_kt: NEON GEMM/GEMV
* New iq2_kt: slightly faster NEON GEMM
* New iq2_kt: Metal - very slow.
It seems Apple Silicon cannot quickly add 4 8-bit ints.
Or I don't know how to do it - but I didn't find anything
in the Metal Shading Language Specification.
So, performance is quite a bit worse than the original trellis.
* Add missing break
* Trying @louiehelm's multiplier
* CPU
* iq3_kt: use integer trellis + CUDA dequantize and MMVQ
* iq3_kt: MMQ
* iq3_kt: AVX2 GEMM
* iq3_kt: AVX2 GEMV
* The trellis quants now need super-blocks of 256, so we need a check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iq1_s_r4: CUDA dequantize
* iq1_s_r4: CUDA GEMV
* iq1_s_r4: MMQ on CUDA
Requires Turing or better (will fall back to dequantize+cuBLAS on older cards).
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* WIP
* WIP
* WIP
* Testing Trellis quantization
Using 12 bits per 8 weights I get a better rmse than
iq2_xxs. I still need to see how quantizing the group-of-8
scales will affect accuracy. By AVX2 SIMDifying the search
for the best code, LLaMA-3.1-8B gets quantized in 130 seconds
on the Ryzen-7950X CPU - sluggish but still acceptable.
* Testing Trellis quantization: 4-bit quantized block scales
rmse increases by just 3%, so this is beating iq2_xss in terms
of rmse at the same 2.0625 bpw.
* Testing Trellis quantization: playing with scales and generators
* iq2_kt: quantize / dequantize
I now see that I was comparing apples to oranges:
iq2_xxs was using a weight of sigma^2/4 + x^2, while
the Trellis approach wasn't (weight = 1). Once I use the same weight,
iq2_kt is actually slightly worse than iq2_xxs in terms
of rmse, so does not look promising at this point.
Also, once each group of 8 Trellis values no longer has a
constant sum(q^2) that we can precompute, quantization
becomes significantly slower (476 seconds for LLaMA-3.1-8B).
* iq2_kt: CUDA dequantize
so we can run perplexity calcs.
As already indicated by rmse, the 2-bit trellis approach is
quite a bit worse than iq2_xxs.
* WIP
* WIP
* WIP - try larger blocks
With blocks of 32 and 16 bits per groups of 8 the brute force
seach becomes prohibitive in terms of CPU time (30+ minutes
for 8B LLaMA after SIMDifying with AVX2). The trick is to
group the points in clusters, find the nearest cluster,
and only search within the cluster.
* iq2_kt - this is better
Using blocks of 32 and 16 bits per group of 8 weights
it beats iq2_xxs in terms of PPL by a significant margin.
It is 0.0625 bpw larger, but even if we go to 15 bits per
group od 8 (so 0.0625 bpw less than iq2_xxs), PPL is still
lower.
* iq2_kt - even better
Re-quantize after determining block scales
(at the epxense of much longer quantization time).
* iq2_kt: CUDA dot product
Implemented as DMMV.
Very slow - just 81 t/s for LLaMA-3.1-8B.
Then again, Q2_K_S with forced to use DMMV only
gets 112 t/s vs 145 t/s via MMVQ. My memory is that
when the DMMV kernels were properly maintained/used,
DMMV was about on par with MMVQ for k-quants on my GPU.
* iq2_kt: very slightly faster CUDA dot product
* iq2_kt: f16 CUDA dot product
We arrive at 112 t/s.
* iq2_kt: faster f16 CUDA dot product
We arrive at 139 t/s (no FA), and 149 t/s (FA).
My RTX-4080 is ~20% slower than the RTX-6000 quoted in the
QTIP repository, so with FA (which I'm sure they also used)
we are at around ~180 t/s on their GPU, so almost matching
their performance.
* iq2_kt: faster f16 CUDA dot product
We arrive at 146 t/s (no FA), and 158 t/s (FA).
This is measured for LLaMA-3.1-8B with output.weight
left as f16.
* Minor
* Adding iq3_kt
3.125 bpw. So far does not look good on the PPL vs bpw plot.
* Forgotten change
* WIP
* WIP
* iq3_kt WIP: slowly improving
PPL(LLaMA-3.1-8B-Instruct, 8192) is now 6.8322, which is
starting to be competitive/slightly better than other quants.
* WIP
* iq3_kt WIP: slowly improving
PPL(LLaMA-3.1-8B-Instruct, 8192) is now 6.7892
* iq3_kt WIP: slowly improving
PPL(LLaMA-3.1-8B-Instruct, 8192) is now 6.7689 after shrinking
by 0.015 bpw by using iq4_k instead of q5_k for attn_v.
* iq3_kt WIP: speed up quantization
Nearly 60% improvement of quantization speed by having the
points nelonging to a cluster copied to contiguous memory
during initialization, and then accessed sequantially while
searching for the closest point. LLaMA-3.1-8B now gets
quantized in ~150 seconds on the Ryzen-5975WX.
* iq3_kt speed up quantization
Same trick as last commit applied to iq2_kt. Here we get
an even larger speedup: quantization time on the Ryzen-5975WX
for LLaMA-3.1-8B drops to 195 seconds from 375 seconds!
* iq3_kt: CUDA dot product
* iq2_kt: SOTA
We arrive at
PPL(LLaMA-3.1-8B-Instruct, 8192) = 9.2406
PPL(LLaMA-2-7B, 4096) = 6.4179
* iq2_kt: SOTA
We arrive at
PPL(LLaMA-3.1-8B-Instruct, 8192) = 9.1642
PPL(LLaMA-2-7B, 4096) = 6.3920
* Adding iq4_kt - not competitive at this point
* WIP
* WIP
* iq4_kt: CUDA dot product
* iq4_kt: minor tweaks
* iq2_kt: SOTA
We arrive at
PPL(LLaMA-3.1-8B-Instruct, 8192) = 9.1642
PPL(LLaMA-2-7B, 4096) = 6.3920
* iq2_kt: SOTA
We arrive at
PPL(LLaMA-3.1-8B-Instruct, 8192) = 9.0297
PPL(LLaMA-2-7B, 4096) = 6.3913
Ah, quantization is faster too. About 20% faster.
* iq3_kt: small improvements and faster quantization
* iq2_kt: SOTA
We arrive at
PPL(LLaMA-3.1-8B-Instruct, 8192) = 8.9627
PPL(LLaMA-2-7B, 4096) = 6.3825
Quantization is faster too: ~200 seconds for LLaMA-3.1-8B
on Ryzen-5975WX.
* iq3_kt: small progress
* WIP
* iq4_kt: go to 4.0 bpw
15 bits per group of 4, plus 8 bit scales ifor blocks of 32.
This gives a slightly better PPL than iq4_kss.
* iq4_kt: very slightly better
at the expense of much longer quantization time.
* iq4_kt: failed attemt to adjust CUDA dot product
It was working for 4.125 bpw. But after changing to 4.0 bpw
there is something wrong and I don't see the bug.
* DRY
* DRY
* iq4_kt: CUDA dot product works
* DRY
* Report actual bpw
* Minor tweaks
* Checkpoint
Go to groups of 8 for iq3_kt. 2 x 8 = 16 bits for the magnitude
plus 1 bpw for the sign. It goves a visible improvement in the
PPL vs bpw plot, but that comes at the expense of much longer
quantization time (7.5 minutes for LLaMA-3.1-8B on the Ryzen-5975WX).
I also notices that the 3INST generator is not actually generating a
Gaussian distribution. But going to a better generator means
readjusting all the hyper-parameters, so leaving it for later.
* WIP for IQ2_KT
* WIP - working basic iq2_kt
* still super slow (0.17t/s eval)
* flatten 3inst iters + avx2 (0.3t/s eval)
* iq3_kt (0.3t/s eval) and renames
* wip buggy iq4_KT
* fix (0.22t/s eval)
* naming and remove unused fn
* cleanup
* more cleanup
* delete unused and noncompiling mmvq functions
* Some performance tweaks
* Slighty faster iq2_kt
* port Trellis struct to iq3_kt, iq4_kt
* oops untracked files
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iq5_ks: basics
* iq5_ks: quantize
* iq5_ks: CUDA dequantize works
* iq5_ks: dot product works on CUDA
* iq5_ks: MMQ works
* iq5_ks: Zen4
* iq5_ks: AVX2
But is is not quite right, just like iq4_k, iq5_k, iq6_k, iq4_ks.
All these need fixing on AVX2.
* iq5_ks: NEON
* iq5_ks: Metal dequantize
* iq5_ks: Metal dot product
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Adapting iq2_bn to work without separate scale tensors
Why? It is becoming burdensome to maintain the special Bitnet
conversion in convert_hf_to_gguf.py, so I thnk it is better
to make iq1_bn and iq2_bn just work with the mainline
conversion script (which does not generate scales).
* Adapting iq1_bn to work without separate scale tensors
* Adapting iq2_bn: CUDA dequantize
* Adapting iq2_bn: CUDA works
* Adapting iq1_bn: CUDA works
* Adapting iq1_bn, iq2_bn: NEON
* Adapting iq1_bn, iq2_bn: Metal
Dequantize works, but there is still something wrong
with the dot products.
* WIP
Absoolutely don't see what is wrong with the iq1_bn and iq2_bn
vector dot product kernels.
* Remove iq1_tn and iq2_tn - Part 1
Now that iq1_bn and iq2_bn have per row scales, there is no
reason to also have iq1_tn and iq2_tn.
* Remove iq1_tn and iq2_tn - Part 2
* Bitnet: use the standard llm_build_kv to build self attention
My main motivation was to enable FA. But FA does not work anyway
because head size is 100 for the Botnet ternary models
(and I had forgotten this little detail).
* Revert "Avoid rebuild of GGML graph for each token (#98)"
This reverts commit f2d315b46f.
As far as I can tell, the commit breaks Metal TG.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iq4_kss: WIP
* iq4_kss: CUDA dequantize works
So we can run perplexity. Sadly, the result does not look good
on the bpw vs quantization error plot.
* iq4_kss: slightly better quantization
* iq4_kss: another small quantization improvement
* iq4_kss: CUDA works
TG-128 performance is very decent with 131 t/s for LLaMA-3.1-8B.
In comparison, we have 123 t/s for q4_0 and 128 t/s for iq4_ks.
I.e., the reduced model size more than offsets the additional
bit fiddling required for iq4_kss.
* iq4_kss: new bit arrangement - CUDA and Zen4 work
Did not lose performance on CUDA. Zen4 is decent, but not great:
PP-512(LLaMA-3.1-8B) = 163 t/s.
TG-128 is of course better than other 4-bit quants due to smaller model size.
We get 14.5 t/s @ 8 threads.
* iq4_kss: ARM_NEON. Predictably very slow
* iq4_kss: Metal
PP is not too bad - just 10% slower than q4_0.
But TG is 30% slower, i.e., predictably bad.
* iq4_kss: somewhat faster Metal dot product
45.75 t/s -> 48.75 t/s.
Still 22% slower than q4_0
* iq4_kss: AVX2
Bad, but better than I expected.
PP-512(LLaMA-3.1-8B) = 167 t/s on the Ryzen-5950X.
I.e., with 32 AVX2 threads we get the performance of
16 Zen4 threads.
* iq4_kss: very slightly faster Metal dot product
48.7 t/s -> 49.3 t/s
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iq4_k_xxs: basics
* WIP + adding iq3_kl quantization mix
* iq4_xxs: this looks very viable compared to iq4_xs
At the same 4.25 bpw PPL is always better, for some models
significantly better. I'll rename to iq4_ks and keep it.
* iq4_xxs: CUDA dot product
We get TG-128 = 126 t/s for LLaMA-3.1-8B, compared to 123 t/s for q4_0.
* iq4_xxs: scalar CPU dot product
Also fix the breakage I caused with the dedicated work buffer
quantization portion when the multiplication is not done
via iqk_mul_mat.
* iq4_xxs: Zen4
I noticed that iq4_xs is wrong on Zen4 (and possibly AVX2).
Again the same mistake of packing int32_t back to int16_t,
which overflows occasionally (just occasionally, that's why the
result doesn't look completely wrong, so I didn't notice).
* Fix iq4_xs (Zen4)
* iq4_xxs: AVX2
* iq4_xxs: ARM_NEON
* iq4_xxs: Metal
* iq4_xxs: slightly faster TG on Metal
* iq4_xxs: rename to iq4_ks
After all, tt is a smaller variant of iq4_k.
* iq3_kl: use iq4_ks instead of iq4_k/iq4_xs
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Adding q6_0 - basics + AVX2/Zen4 working
* Adding q6_0: CUDA dequantize works, but not mmvq
* Adding q6_0: CUDA mmvq works
* Adding q6_0: CUDA cpy, so Q6_0 can be used for KV-cache
* Add q6_0 to CPU flash attention
Disappointing result: for LlaMA-3.2-1B, q6_0 K- and V-cache
gives about the same PPL as q8_0 K-cache and q4_0 V-cache,
while needing the exact same RAM.
I.e., what was the point?
* q6_0: slightly better kv-cache result
Better than q8_0+q4_0, but not as good as q8_0+iq4_nl
* q6_0: works on ARM_NEON
* q6_0: dequantize works on Metal, but not vector dot product
* q6_0: it now works on Metal
Outperforms q5_0 by a significant margin. E.g.
| model | size | params | backend | ngl | threads | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | ------------: | ---------------: |
| llama 8B Q6_0 | 6.08 GiB | 8.03 B | Metal | 100 | 4 | tg128 | 44.02 ± 0.08 |
| llama 8B Q5_0 | 5.21 GiB | 8.03 B | Metal | 100 | 4 | tg128 | 40.13 ± 0.12 |
| llama 8B Q6_0 | 6.08 GiB | 8.03 B | Metal | 100 | 4 | pp512 | 500.55 ± 0.32 |
| llama 8B Q5_0 | 5.21 GiB | 8.03 B | Metal | 100 | 4 | pp512 | 448.02 ± 0.27 |
* q6_0: can now be used for kv-cache on Metal
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iq2_tn: TriLM specific 2.0625 bpw quantization
Quantize/dequantize/scale dot product.
I get 46 t/s for the TriLM-3.9B with any SIMD!
Finally a compiler doing a decent job auto-vectorizing the
scalar implementation.
* iq2_tn: AVX512
Just reusing the k-quants template gets us to PP-512 = 376 t/s,
TG-128 = 47.6 t/s for TriLM-3.9B.
* iq2_tn: AVX512
With this tweak we get to PP-512 = 431 t/s.
* iq2_tn: AVX512
With this tweak we get TG-128 = 19.58 / 35.18 t/s for 1 / 2 threads.
At 4 threads we saturate at 48.41 t/s, and then performance slowly
degrades with increasing number of threads.
* iq2_tn: AVX2
PP512 = 440 t/s on the Ryzen-5975WX.
We should be able to do better.
* iq2_tn: initial NEON version
* iq2_tn: NEON
For TriLM-3.9B running on the M2-Max we get PP-512 = 193.5 t/s,
TG-128 = 75.5 t/s. This is in line with what we have for
iq2_bn ant 3.3B Bitnet.
* iq2_tn: Metal
For TriLM-3.9B on a 30-core M2-Max we get PP-512 = 890 t/s,
TG-128 = 98.5 t/s.
* iq2_tn: CUDA
For TriLM-3.9B running on RTX-4080 we get PP-512 = 9936 t/s,
TG-128 = 299.2 t/s.
* iq2_tn: AVX2 PP improvement
We now get PP-512 = 490.73 t/s for TriLM-3.9B on the Ryzen-5975WX.
We have PP-512 = 636.61 t/s for Bintnet-3B quantized with iq2_bn.
Bintnet-3B is actually 3.4B, TriLM-3.9B is 3.99B, so we would
expect 3.43/3.99 * 636 = 546 t/s, so it seems we still have something
that is not quite optimal in iq2_tn.
* iq2_tn: small NEON improvement
For TriLM-3.9B we now get PP-512 = 206.6 t/s and TG-128 = 76.4 t/s.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* iq4_k: basics
* quantize/dequantize works
* CUDA dequantize works and one can run PPL calcs. I get
PPL = 6.5258 for LlaMA-3.1-8B, which is 1.77% above fp16.
In comparison, q4_K_S (same size) is 2.88% above fp16.
* TG on CUDA does not work. Johannes has changed the way i-quant dot
products are done, so need to sort out what he had in mind
* iqk_mul_mat is not implemented.
* iq4_k: TG now works on CUDA
* iq4_k: AVX512 implementation
For LLaMA-3.1-8B we get PP-512 = 182.6 t/s, TG-128 = 13.6 t/s,
so almost the same as q4_K_S.
* iq4_k: AVX2 implementation
For LLaMA-3.1-8B we get PP-512 = 203.1 t/s, TG-128 = 12.9 t/s
on the Ryzen-5975X.
* iq4_k: NEON implementation
For LLaMA-3.1-8B we get PP-512 = 60.7 t/s, TG-128 = 25.0 t/s
on the M2-Max. TG is on par with q4_K_S, PP is ~10% slower.
* iq4_k: Metal implementation
For LLaMA-3.1-8B we get PP-512 = 445 t/s, TG-128 = 46.3 t/s
on a 30-core M2-Max GPU. This is to be compared with (currently)
PP-512 = 460 t/s, TG-128 = 51 t/s for q4_K_S.
* iq4_k: scalar dot product
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Merging mainline - WIP
* Merging mainline - WIP
AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.
* Merging mainline - fix Metal
* Remove check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
